diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
index 32ad602907d459ebc21681dc2b44508106bb1e63..e8660a41abe5dcffcd6fefb341c4d47381b1eb5b 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,19 @@
----
-license: other
-license_name: eva-llama3.3
-license_link: LICENSE
----
+---
+license: other
+license_name: eva-llama3.3
+language:
+- en
+- fr
+- it
+- pt
+- hi
+- es
+- th
+- de
+base_model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
+base_model_relation: quantized
+library_name: mlc-llm
+pipeline_tag: text-generation
+---
+
+3-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [EVA-LLaMA-3.33-70B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1) for inference with the [Private LLM](https://privatellm.app/) app.
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2f98e357c05745bf2cf79816dbac3b1d79de5789
--- /dev/null
+++ b/config.json
@@ -0,0 +1,5 @@
+{
+  "quantization_config": {
+        "bits": 3
+    }
+}
diff --git a/ndarray-cache.json b/ndarray-cache.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec89aad550be410614cd4b6d42d4754967486d82
--- /dev/null
+++ b/ndarray-cache.json
@@ -0,0 +1,12343 @@
+{
+    "metadata": {
+        "ParamSize": 805,
+        "ParamBytes": 31776318464.0,
+        "BitsPerParam": 3.04023285660184
+    },
+    "records": [
+        {
+            "dataPath": "params_shard_0.bin",
+            "format": "raw-shard",
+            "nbytes": 420679680,
+            "records": [
+                {
+                    "name": "lm_head.q_weight",
+                    "shape": [
+                        128256,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 420679680,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6e8c04d5fed4ec1d0fcd018c18079f9d"
+        },
+        {
+            "dataPath": "params_shard_1.bin",
+            "format": "raw-shard",
+            "nbytes": 52584960,
+            "records": [
+                {
+                    "name": "lm_head.q_scale",
+                    "shape": [
+                        128256,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 52584960,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0b46e7cf7e44f0d1f258c1ce3e332f08"
+        },
+        {
+            "dataPath": "params_shard_2.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.78.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ac22d40312ed9f8d8d3f16675851130f"
+        },
+        {
+            "dataPath": "params_shard_3.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.79.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a7415891af89927cf0ef93a374c4df5f"
+        },
+        {
+            "dataPath": "params_shard_4.bin",
+            "format": "raw-shard",
+            "nbytes": 23560192,
+            "records": [
+                {
+                    "name": "model.layers.78.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.78.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 16384
+                },
+                {
+                    "name": "model.layers.78.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.79.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23543808
+                }
+            ],
+            "md5sum": "3e4568870139d661b05c79be7fafab21"
+        },
+        {
+            "dataPath": "params_shard_5.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.79.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "018922d5ddd66d7f3f455b8006da50ca"
+        },
+        {
+            "dataPath": "params_shard_6.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.79.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2c9567fa54576f611da7cf084e04365a"
+        },
+        {
+            "dataPath": "params_shard_7.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.79.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f3dae7d3271ccb2d590d03347469c8ad"
+        },
+        {
+            "dataPath": "params_shard_8.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.79.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "10569b7947e1e1c3805ba8f6da3252fd"
+        },
+        {
+            "dataPath": "params_shard_9.bin",
+            "format": "raw-shard",
+            "nbytes": 420679680,
+            "records": [
+                {
+                    "name": "model.embed_tokens.q_weight",
+                    "shape": [
+                        128256,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 420679680,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bb619cfb8d8e53d66251167b9b86dce1"
+        },
+        {
+            "dataPath": "params_shard_10.bin",
+            "format": "raw-shard",
+            "nbytes": 52584960,
+            "records": [
+                {
+                    "name": "model.embed_tokens.q_scale",
+                    "shape": [
+                        128256,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 52584960,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7d675407607ff634eba60b0405b07fd8"
+        },
+        {
+            "dataPath": "params_shard_11.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.0.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4fa85eb5836f24fee99a972a575c5e57"
+        },
+        {
+            "dataPath": "params_shard_12.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.0.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "af024a0c7fdd959670560978669334e5"
+        },
+        {
+            "dataPath": "params_shard_13.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.0.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e375906f212aa331789ae4355f46c946"
+        },
+        {
+            "dataPath": "params_shard_14.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.0.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "471448818dac9591ff99a346a87abfdb"
+        },
+        {
+            "dataPath": "params_shard_15.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.79.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.79.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.79.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.79.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.norm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.0.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.0.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.0.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "1b8e82625ae889ddab1e5e17f594099c"
+        },
+        {
+            "dataPath": "params_shard_16.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.0.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.0.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "8368428c494d46747c416a7893c6657a"
+        },
+        {
+            "dataPath": "params_shard_17.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.1.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "08526ff95118cfe7f1e7f64cb67db7b6"
+        },
+        {
+            "dataPath": "params_shard_18.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.1.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "76dda1cca6913e9be47e4ae7e5c0f489"
+        },
+        {
+            "dataPath": "params_shard_19.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.1.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c2ca8574185ff4fbe321145cf5a533f5"
+        },
+        {
+            "dataPath": "params_shard_20.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.0.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.1.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.1.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 26869760
+                }
+            ],
+            "md5sum": "e6650b25ef7ab06cd9df83b31b61656a"
+        },
+        {
+            "dataPath": "params_shard_21.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.1.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1d012ff4d5bb203a8a1f1048730b936e"
+        },
+        {
+            "dataPath": "params_shard_22.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.2.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c3ebf773d1c1c356962c815ae67cb74f"
+        },
+        {
+            "dataPath": "params_shard_23.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.2.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "03c0d1905229e4c53c4117d94a6bdab8"
+        },
+        {
+            "dataPath": "params_shard_24.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.2.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5de52cffaf6a9f7b2936eb91c3b09ce0"
+        },
+        {
+            "dataPath": "params_shard_25.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.2.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4a5fca4650d1d731a72693db331819a2"
+        },
+        {
+            "dataPath": "params_shard_26.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.2.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4f72d64a2da31f48d5c7b5d2a59d6132"
+        },
+        {
+            "dataPath": "params_shard_27.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.1.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.1.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.1.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.1.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.2.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.2.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 15155200
+                },
+                {
+                    "name": "model.layers.2.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26902528
+                },
+                {
+                    "name": "model.layers.2.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 26918912
+                }
+            ],
+            "md5sum": "273a96d3bf99f56289bd6b8a6ddbd999"
+        },
+        {
+            "dataPath": "params_shard_28.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.3.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8fa2a11fc9f4215fd96ae49191b5f347"
+        },
+        {
+            "dataPath": "params_shard_29.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.3.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f71657cf80a6415bab739c7f84bee3a9"
+        },
+        {
+            "dataPath": "params_shard_30.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.3.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "708b78a14d31e15e2cd47e98a6877123"
+        },
+        {
+            "dataPath": "params_shard_31.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.3.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "03a6b1c92c61f9d9d5a6600225809801"
+        },
+        {
+            "dataPath": "params_shard_32.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.3.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8cede074a2f6ffea50d0486e7d9ce8f5"
+        },
+        {
+            "dataPath": "params_shard_33.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.4.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "03e578cb3e7eb7290bbfafe57b85cc0d"
+        },
+        {
+            "dataPath": "params_shard_34.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.4.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6a4362524f36c35fe302a643fd34207d"
+        },
+        {
+            "dataPath": "params_shard_35.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.10.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "161a3473b3b043564ba85c374a4b5824"
+        },
+        {
+            "dataPath": "params_shard_36.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.2.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.3.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.3.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.3.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.3.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.3.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.4.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.4.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.10.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "c89c101c524be337029eb45afd0d189d"
+        },
+        {
+            "dataPath": "params_shard_37.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.10.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ac7e78b57eb82ad83f35e9d6b6c03342"
+        },
+        {
+            "dataPath": "params_shard_38.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.10.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d85a98cb8bca1fad9c73c7dc05711bd7"
+        },
+        {
+            "dataPath": "params_shard_39.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.10.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "30106c135afdc69b2f5526c0174d32f2"
+        },
+        {
+            "dataPath": "params_shard_40.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.10.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0c4231a7045418b467c8925ca0cb1f6b"
+        },
+        {
+            "dataPath": "params_shard_41.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.11.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5ca592d4b68f444a57fac0e255a13723"
+        },
+        {
+            "dataPath": "params_shard_42.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.11.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e821b3257967d3c08a02957d57b15e44"
+        },
+        {
+            "dataPath": "params_shard_43.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.11.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "252cc69da220a38ea8fbbbda720ffc39"
+        },
+        {
+            "dataPath": "params_shard_44.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.11.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cc6556fffdcaed9b5ea716ff597c799e"
+        },
+        {
+            "dataPath": "params_shard_45.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.10.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.10.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.10.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.10.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.11.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.11.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.11.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31084544
+                }
+            ],
+            "md5sum": "724c88e30dbb44dfa786c4ea6eb29546"
+        },
+        {
+            "dataPath": "params_shard_46.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.11.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.11.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "63a88bf1da0a8eae80c54732441940ff"
+        },
+        {
+            "dataPath": "params_shard_47.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.12.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "46f81c0349033c442d2f338fbe3a0ef2"
+        },
+        {
+            "dataPath": "params_shard_48.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.12.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b8a89a16bc439c49d49cff1bb639663c"
+        },
+        {
+            "dataPath": "params_shard_49.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.9.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9bac663d4dd4a0742e9525b1e588fcfa"
+        },
+        {
+            "dataPath": "params_shard_50.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.9.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "02941565aac3f3e1aa18975e9b1441fd"
+        },
+        {
+            "dataPath": "params_shard_51.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.9.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fc7095374dd89abd31874482f928de41"
+        },
+        {
+            "dataPath": "params_shard_52.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.12.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9ac4f5fb22c163aaff08bdc44170c9c4"
+        },
+        {
+            "dataPath": "params_shard_53.bin",
+            "format": "raw-shard",
+            "nbytes": 22712320,
+            "records": [
+                {
+                    "name": "model.layers.11.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.12.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.12.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 7557120
+                },
+                {
+                    "name": "model.layers.9.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 10915840
+                },
+                {
+                    "name": "model.layers.9.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 10932224
+                },
+                {
+                    "name": "model.layers.9.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22679552
+                },
+                {
+                    "name": "model.layers.12.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22695936
+                }
+            ],
+            "md5sum": "8fb5b08ee48d1c63c231b6a30e22636d"
+        },
+        {
+            "dataPath": "params_shard_54.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.12.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9d08d29d2e6c4b2b36d2fc39066cac39"
+        },
+        {
+            "dataPath": "params_shard_55.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.12.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "16e706fc93d58491ddd466768b80df61"
+        },
+        {
+            "dataPath": "params_shard_56.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.13.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "91242c79b9cbeb7e770454a452b6b32e"
+        },
+        {
+            "dataPath": "params_shard_57.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.13.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3d4c58269ad3a67bc2aee2324adc51a3"
+        },
+        {
+            "dataPath": "params_shard_58.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.13.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "946d362ebd54411a46b791a5534182d0"
+        },
+        {
+            "dataPath": "params_shard_59.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.13.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "431ebc9744934a5f4debb510bd18b766"
+        },
+        {
+            "dataPath": "params_shard_60.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.13.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "14d8a3549bda272fed63a352bbe0a3b4"
+        },
+        {
+            "dataPath": "params_shard_61.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.14.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "060e14291fc0ca448d745764956704a4"
+        },
+        {
+            "dataPath": "params_shard_62.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.12.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.12.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.13.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.13.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.13.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.13.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.13.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "18f76f8bdfcbcc612e4a208befa180ac"
+        },
+        {
+            "dataPath": "params_shard_63.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.14.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e08f52deb357986baafffa7cfdcdeac8"
+        },
+        {
+            "dataPath": "params_shard_64.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.14.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e25d3ab463200e0a942152d2ba4c4db5"
+        },
+        {
+            "dataPath": "params_shard_65.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.14.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7a713429d2f18407665d2eb9c3c222c0"
+        },
+        {
+            "dataPath": "params_shard_66.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.14.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2e7b10babad2e82275d1a23842c8c4ec"
+        },
+        {
+            "dataPath": "params_shard_67.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.15.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7493768f0fefdb08673ec4107a664583"
+        },
+        {
+            "dataPath": "params_shard_68.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.15.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8b97dffbcb86413d649cb7a72ea9a83b"
+        },
+        {
+            "dataPath": "params_shard_69.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.15.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ac58b96ebfdf081bbe9eb72e4ecff646"
+        },
+        {
+            "dataPath": "params_shard_70.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.15.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9140980b507b666dbdae8ca9707ed2be"
+        },
+        {
+            "dataPath": "params_shard_71.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.14.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.14.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.14.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.14.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.14.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.15.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.15.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.15.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "56fa25bb836d0da46f4043d0fea1ef7a"
+        },
+        {
+            "dataPath": "params_shard_72.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.15.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.15.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "8fb078026854ff8a69c6ddfa4afe611c"
+        },
+        {
+            "dataPath": "params_shard_73.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.16.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a00f44deae0c7b44518a8f27c1d1cfd1"
+        },
+        {
+            "dataPath": "params_shard_74.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.16.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f247762adb550f91cf84fd2293330a71"
+        },
+        {
+            "dataPath": "params_shard_75.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.16.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "951ba952417fb17a779375d8a8b5ef55"
+        },
+        {
+            "dataPath": "params_shard_76.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.16.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3fe671f34c4b13ae9a59a06f409203c3"
+        },
+        {
+            "dataPath": "params_shard_77.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.16.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f76c61f88c15543f20144ebb2d875246"
+        },
+        {
+            "dataPath": "params_shard_78.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.17.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9891a0947a9fcc1b8c450e895200b5c1"
+        },
+        {
+            "dataPath": "params_shard_79.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.17.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6b5e8bfcbf664958c21605f03ac78097"
+        },
+        {
+            "dataPath": "params_shard_80.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.17.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1bc5e62bdb3032ef33a13b8ba3fb7999"
+        },
+        {
+            "dataPath": "params_shard_81.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.17.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "99874b07f6c04c763411701dd7e1135b"
+        },
+        {
+            "dataPath": "params_shard_82.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.17.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d0ec25bfcb4f12d45c42b6f0a2dfd6c6"
+        },
+        {
+            "dataPath": "params_shard_83.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.15.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.16.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.16.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.16.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.16.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.16.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.17.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.17.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.17.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "eed152c753c12a043d6f14b243539336"
+        },
+        {
+            "dataPath": "params_shard_84.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.18.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ff5328692d1ecd7558a5e7483f791ed6"
+        },
+        {
+            "dataPath": "params_shard_85.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.18.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "544d48d2e8b3a3f4baa82a2625dd7d8e"
+        },
+        {
+            "dataPath": "params_shard_86.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.18.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4f129fa92b8fab3cb5601aace2262d4a"
+        },
+        {
+            "dataPath": "params_shard_87.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.18.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f9d119c1176f1c1f4ffe813737922e2c"
+        },
+        {
+            "dataPath": "params_shard_88.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.18.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e8e7778700b156cdeafc3f23ba9cd3e3"
+        },
+        {
+            "dataPath": "params_shard_89.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.19.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6a25ef8118da7c3ecf025d44039b16ca"
+        },
+        {
+            "dataPath": "params_shard_90.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.17.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.17.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.18.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.18.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.18.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.18.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.18.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.19.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "9a869ea5812b637c9749129c34eab820"
+        },
+        {
+            "dataPath": "params_shard_91.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.19.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8a7f28cb007d1fde97a415d42be2d179"
+        },
+        {
+            "dataPath": "params_shard_92.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.19.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "aeab82a43ba7d0e0962c79ceb85fe8db"
+        },
+        {
+            "dataPath": "params_shard_93.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.19.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b78419c134ad9908d0282dd9b492c6de"
+        },
+        {
+            "dataPath": "params_shard_94.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.19.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3415b18252e711f8ab3be8e908fba001"
+        },
+        {
+            "dataPath": "params_shard_95.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.20.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "76c294a6b912db17cba1d7226d11206c"
+        },
+        {
+            "dataPath": "params_shard_96.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.20.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "100902667bd767564047c3da2ac2297b"
+        },
+        {
+            "dataPath": "params_shard_97.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.20.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9484edf8379fa58115b5fcc493a6b554"
+        },
+        {
+            "dataPath": "params_shard_98.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.19.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.19.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.19.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.19.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.20.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.20.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.20.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "d7c535193ed3f8951cb8ddf6e7be2152"
+        },
+        {
+            "dataPath": "params_shard_99.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.20.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "da6f72e433608eea9c93dd2a36000c6f"
+        },
+        {
+            "dataPath": "params_shard_100.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.20.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4b7d2c06da9c77447751ecd92e0aae5e"
+        },
+        {
+            "dataPath": "params_shard_101.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.21.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6585693fbdc0e339b291e118d9539ee1"
+        },
+        {
+            "dataPath": "params_shard_102.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.21.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cf6d595819bc45354f1bf19c156005c7"
+        },
+        {
+            "dataPath": "params_shard_103.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.21.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a8fd9ff90fbd231571fad7b2474fd52b"
+        },
+        {
+            "dataPath": "params_shard_104.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.21.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ecabd5c1b414eca7fbbce076f18d56f2"
+        },
+        {
+            "dataPath": "params_shard_105.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.21.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "eb9a1b5e5516afd4941f6e35c7086df3"
+        },
+        {
+            "dataPath": "params_shard_106.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.22.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1f9ab3f7b160b7a91c01b2dcbd978adf"
+        },
+        {
+            "dataPath": "params_shard_107.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.20.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.20.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.21.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.21.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.21.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.21.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.21.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "8bf531817d804d10a9f5815dfc8dc4df"
+        },
+        {
+            "dataPath": "params_shard_108.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.22.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7f221eba69ab447d5f684565466a49d4"
+        },
+        {
+            "dataPath": "params_shard_109.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.22.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3bcc66d8964db210dd1bc178760fcf60"
+        },
+        {
+            "dataPath": "params_shard_110.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.22.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "672fba73078a52c7c162e0f14c468b0f"
+        },
+        {
+            "dataPath": "params_shard_111.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.22.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9983759613868a7685430e3d8fc3779a"
+        },
+        {
+            "dataPath": "params_shard_112.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.23.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "de3869fef2f77a79fdc7b8494c8e50e4"
+        },
+        {
+            "dataPath": "params_shard_113.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.23.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ee7d20ebad1d111ef2d3d10bd64d8fc8"
+        },
+        {
+            "dataPath": "params_shard_114.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.23.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "804cbadb69c3d45a74b6108f11676d3f"
+        },
+        {
+            "dataPath": "params_shard_115.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.23.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a5d89a34e16997f2e784c3ddc0ce2104"
+        },
+        {
+            "dataPath": "params_shard_116.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.22.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.22.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.22.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.22.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.22.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.23.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.23.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.23.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "e93d6f3136b6d9f1e9e6eef6835d3f60"
+        },
+        {
+            "dataPath": "params_shard_117.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.23.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.23.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "e0c5750cbcd194b817f811a8a2c66fae"
+        },
+        {
+            "dataPath": "params_shard_118.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.24.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c16d54aab0e6de45f199afba25f983e3"
+        },
+        {
+            "dataPath": "params_shard_119.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.24.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9c41e15cf8af89e2c23b3ff5e827335a"
+        },
+        {
+            "dataPath": "params_shard_120.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.24.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b4a3dea8b1f38c95c61eeb4640658986"
+        },
+        {
+            "dataPath": "params_shard_121.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.24.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3644b4a4d0e57fc28be8cd45b63b4136"
+        },
+        {
+            "dataPath": "params_shard_122.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.24.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f554b02f604d310cbba86bd28b35a23a"
+        },
+        {
+            "dataPath": "params_shard_123.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.25.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "433341713969856cf8298f75c369104b"
+        },
+        {
+            "dataPath": "params_shard_124.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.25.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "28378e9461e40c2c5fe2041e113c54ce"
+        },
+        {
+            "dataPath": "params_shard_125.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.25.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4dc2a47ca3a461f51908582eef9d5048"
+        },
+        {
+            "dataPath": "params_shard_126.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.25.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "56484c240cfaba57f257ef8a365ffc46"
+        },
+        {
+            "dataPath": "params_shard_127.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.25.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c034722cf978d65e24d5a092c1f52fcf"
+        },
+        {
+            "dataPath": "params_shard_128.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.23.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.24.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.24.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.24.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.24.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.24.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.25.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.25.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.25.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "d7a372241eed2d8adbf68cf930647d81"
+        },
+        {
+            "dataPath": "params_shard_129.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.26.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "adecfb1c577c9b4e5a38b34466a2b750"
+        },
+        {
+            "dataPath": "params_shard_130.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.26.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4abc4e9225584eedf7d858d77faef617"
+        },
+        {
+            "dataPath": "params_shard_131.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.26.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1a26bf91683ada7b508858fdd951d9d9"
+        },
+        {
+            "dataPath": "params_shard_132.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.26.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3de2bc15112eee9f3d31a3436c978ea3"
+        },
+        {
+            "dataPath": "params_shard_133.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.26.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0214ea441f67ec1ffc29eda66ded00a6"
+        },
+        {
+            "dataPath": "params_shard_134.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.27.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2fc5a8e9be7d2745e76edf2e4bdf9c4a"
+        },
+        {
+            "dataPath": "params_shard_135.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.25.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.25.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.26.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.26.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.26.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.26.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.26.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.27.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "ca881791ae75e2c8080fc17b072eb520"
+        },
+        {
+            "dataPath": "params_shard_136.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.27.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5181ec2ae0022e9b6467a6ab6f45ec2d"
+        },
+        {
+            "dataPath": "params_shard_137.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.27.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d8b7ee4ea5ee1eb4c692f6a172f52e55"
+        },
+        {
+            "dataPath": "params_shard_138.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.27.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0523cf3c0de633b1cb24aa758acf78f9"
+        },
+        {
+            "dataPath": "params_shard_139.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.27.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fdee9c27b9c3c7eb76f4bfb1488c189e"
+        },
+        {
+            "dataPath": "params_shard_140.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.28.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "293127081cbc4e458bba977905ac59b3"
+        },
+        {
+            "dataPath": "params_shard_141.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.28.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "64706663b51853b27dfa8ba25a35f9ce"
+        },
+        {
+            "dataPath": "params_shard_142.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.28.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "801abc0b8141050daffd31f60d5bbcef"
+        },
+        {
+            "dataPath": "params_shard_143.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.27.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.27.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.27.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.27.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.28.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.28.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.28.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "7608057ac152d8092386c27f162a1f46"
+        },
+        {
+            "dataPath": "params_shard_144.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.28.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7832f9eb956ec192ef5ae60459afed9f"
+        },
+        {
+            "dataPath": "params_shard_145.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.28.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4bffe8bb9f4a3b54572a0b62d3759c07"
+        },
+        {
+            "dataPath": "params_shard_146.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.29.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b96c5bd86df2b3886e8c9c620f2255cf"
+        },
+        {
+            "dataPath": "params_shard_147.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.29.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f994da70a7f5c3f708a51f8b76baa087"
+        },
+        {
+            "dataPath": "params_shard_148.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.29.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "48ff21aef5ff018cf8b5c6d681b57295"
+        },
+        {
+            "dataPath": "params_shard_149.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.29.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "293c1e83d6de54c20bba686aaa16a253"
+        },
+        {
+            "dataPath": "params_shard_150.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.29.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "29e647c6991d6d2036f405b66585bd8c"
+        },
+        {
+            "dataPath": "params_shard_151.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.30.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3c5ad8495e1ae15b223c732d90542766"
+        },
+        {
+            "dataPath": "params_shard_152.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.28.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.28.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.29.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.29.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.29.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.29.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.29.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "a1807eb15a1b5c9139e6b1c9a452aee8"
+        },
+        {
+            "dataPath": "params_shard_153.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.30.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cc3ff9fb7a41cbf08f56804d639adba0"
+        },
+        {
+            "dataPath": "params_shard_154.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.30.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "af7b8ef87c76e3f1a2df8dc11fe18dc2"
+        },
+        {
+            "dataPath": "params_shard_155.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.30.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1f3bcc3c573a6e5e005998e54591bbc3"
+        },
+        {
+            "dataPath": "params_shard_156.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.30.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "84481b923dc25ad5673849e2448f7fc4"
+        },
+        {
+            "dataPath": "params_shard_157.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.31.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "73d16746eec5035fee8fd061d8f54c3a"
+        },
+        {
+            "dataPath": "params_shard_158.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.31.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7ae68c220ae4134930781a671d9a242f"
+        },
+        {
+            "dataPath": "params_shard_159.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.31.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "59cbbd598888ab546378767a663a1f79"
+        },
+        {
+            "dataPath": "params_shard_160.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.31.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6156cf6025a8eca8be42815090e38cbb"
+        },
+        {
+            "dataPath": "params_shard_161.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.30.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.30.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.30.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.30.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.30.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.31.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.31.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.31.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "a31901a8758c67b6dc88ec70492cd0bc"
+        },
+        {
+            "dataPath": "params_shard_162.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.31.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.31.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "e4538cdb075e280438f6ecd5dcf466dd"
+        },
+        {
+            "dataPath": "params_shard_163.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.32.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6869f60cdf2a0c137afc83623532b7cd"
+        },
+        {
+            "dataPath": "params_shard_164.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.32.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e42e73f3a05976532ecbd57a0e945bf1"
+        },
+        {
+            "dataPath": "params_shard_165.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.32.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ce43b8d8781d8cd084ac3224d55c7cea"
+        },
+        {
+            "dataPath": "params_shard_166.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.32.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7d13b772139202ae531231c7b725e7d8"
+        },
+        {
+            "dataPath": "params_shard_167.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.32.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "eaeaf8cb8c584ad6bfc03e6404c42def"
+        },
+        {
+            "dataPath": "params_shard_168.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.33.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fd7ccb2739884d50b3044180cbef1839"
+        },
+        {
+            "dataPath": "params_shard_169.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.33.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a1b7876974fe9250b3b6b4cb3e2c3147"
+        },
+        {
+            "dataPath": "params_shard_170.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.33.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "08bfdd8847c7bd1f3c357d77ce19461b"
+        },
+        {
+            "dataPath": "params_shard_171.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.33.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6596ff3d6cae51c89aadf44e955165b6"
+        },
+        {
+            "dataPath": "params_shard_172.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.33.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "26db7512296a7c9932620f28860c8488"
+        },
+        {
+            "dataPath": "params_shard_173.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.31.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.32.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.32.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.32.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.32.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.32.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.33.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.33.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.33.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "1e4172fba5c52141fd21998c764c8743"
+        },
+        {
+            "dataPath": "params_shard_174.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.34.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fec1dbcda71ca75f09f5f38ae0aed874"
+        },
+        {
+            "dataPath": "params_shard_175.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.34.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1a7a7f9a7036b8af1d105495b0cf73f0"
+        },
+        {
+            "dataPath": "params_shard_176.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.34.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3b60c2a4755edcde67ddfea331db0109"
+        },
+        {
+            "dataPath": "params_shard_177.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.34.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2ec72814f7b3e45c758b8baab7723a6d"
+        },
+        {
+            "dataPath": "params_shard_178.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.34.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a1973b18ac64fd5cf2d11dc2f2b6adec"
+        },
+        {
+            "dataPath": "params_shard_179.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.35.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c1add1c038682d96f19ec41d5836bc56"
+        },
+        {
+            "dataPath": "params_shard_180.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.33.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.33.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.34.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.34.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.34.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.34.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.34.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.35.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "c3dc89bc83a8a0bc134722328e5631cd"
+        },
+        {
+            "dataPath": "params_shard_181.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.35.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3ff864e67b9327a3f11f768da38f7040"
+        },
+        {
+            "dataPath": "params_shard_182.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.35.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4ed6a1a016ea8dd2d26529318e952b63"
+        },
+        {
+            "dataPath": "params_shard_183.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.35.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "52d7d4017b6a6b8f305110543982c419"
+        },
+        {
+            "dataPath": "params_shard_184.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.35.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "abc5ebdd7976d763bd83c339f3eb9434"
+        },
+        {
+            "dataPath": "params_shard_185.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.36.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6ce7f5cc002c6aada594fd013f0ac03b"
+        },
+        {
+            "dataPath": "params_shard_186.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.36.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "850e9d34e3635c60e8c2028db1ce2f60"
+        },
+        {
+            "dataPath": "params_shard_187.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.36.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8ea70761d7152b54423e53894585318d"
+        },
+        {
+            "dataPath": "params_shard_188.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.35.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.35.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.35.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.35.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.36.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.36.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.36.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "764ceddcc95230db106a26d8a7808c7a"
+        },
+        {
+            "dataPath": "params_shard_189.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.36.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5dde80703147fe74ea08a37a148b2daa"
+        },
+        {
+            "dataPath": "params_shard_190.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.36.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fa5d6f29c476292847f8cb4ba2ef6e3f"
+        },
+        {
+            "dataPath": "params_shard_191.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.37.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "34f57455fa589ea81d120e1b747562a0"
+        },
+        {
+            "dataPath": "params_shard_192.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.37.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b23df39129d7fb1d3d8994ad13623c2c"
+        },
+        {
+            "dataPath": "params_shard_193.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.37.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "827428128cadde00a62656aa10c35860"
+        },
+        {
+            "dataPath": "params_shard_194.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.37.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fb7a6912753b788afed26a13d6064eb0"
+        },
+        {
+            "dataPath": "params_shard_195.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.37.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d90775d2fe2e78af058d18e69abefe28"
+        },
+        {
+            "dataPath": "params_shard_196.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.38.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d2af2fad4b2b4c2598e4d8787bdf0f36"
+        },
+        {
+            "dataPath": "params_shard_197.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.36.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.36.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.37.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.37.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.37.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.37.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.37.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "c2eed1a24341c7ee8d2cb2745a0ea0a8"
+        },
+        {
+            "dataPath": "params_shard_198.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.38.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f4156281aedbfa9f196aeade699fdec6"
+        },
+        {
+            "dataPath": "params_shard_199.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.38.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d273e47f6f04078e4540483effc0f2a8"
+        },
+        {
+            "dataPath": "params_shard_200.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.38.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9a14bda63427f6ca1dbcf93de0e54eaf"
+        },
+        {
+            "dataPath": "params_shard_201.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.38.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "715c5d9b66186ce540817e4333934127"
+        },
+        {
+            "dataPath": "params_shard_202.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.39.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "aeaf0b516518475838e94419e85c81a3"
+        },
+        {
+            "dataPath": "params_shard_203.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.39.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0da3f1e97f152a2f6e1f2ec05b8e118d"
+        },
+        {
+            "dataPath": "params_shard_204.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.39.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e1e157c53723c9513c54189c31a7519f"
+        },
+        {
+            "dataPath": "params_shard_205.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.39.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a2f6beb3adac6b1c9b59a01aaa1e1543"
+        },
+        {
+            "dataPath": "params_shard_206.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.38.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.38.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.38.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.38.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.38.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.39.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.39.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.39.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "6469d1c07c1292f5d4a49b63af9964d7"
+        },
+        {
+            "dataPath": "params_shard_207.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.39.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.39.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "fea0f3d0e2bd4c49322cf40c077b8aa4"
+        },
+        {
+            "dataPath": "params_shard_208.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.40.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3a8f8e9017bda402988e8b16dd547ab1"
+        },
+        {
+            "dataPath": "params_shard_209.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.40.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0e44da8edb1f04e31d404e579401e942"
+        },
+        {
+            "dataPath": "params_shard_210.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.40.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "dcebbfa1f9828c6f256b4c0de9bbd511"
+        },
+        {
+            "dataPath": "params_shard_211.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.40.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "76951d87fb3727b1bc7080f437f3e0f5"
+        },
+        {
+            "dataPath": "params_shard_212.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.40.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7bd3b54d4bbff1137c150c5d1f5fd1f7"
+        },
+        {
+            "dataPath": "params_shard_213.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.41.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ab66b0ac296c9d0559e61697f805408b"
+        },
+        {
+            "dataPath": "params_shard_214.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.41.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "745a09979624f1b49ede383e91663fc6"
+        },
+        {
+            "dataPath": "params_shard_215.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.41.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b6ccc2a2b88a47baccdb5984698d28e2"
+        },
+        {
+            "dataPath": "params_shard_216.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.41.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "737f06aed72ca1adfb2042871382e84e"
+        },
+        {
+            "dataPath": "params_shard_217.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.4.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c4da58ed48e5dcaf1771ad9367f7c2cf"
+        },
+        {
+            "dataPath": "params_shard_218.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.39.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.40.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.40.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.40.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.40.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.40.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.41.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.41.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.4.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "d8c69506764ef5b3cec95c49075d5b6f"
+        },
+        {
+            "dataPath": "params_shard_219.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.4.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e3aeee88ce69df5439780fc6031e9d43"
+        },
+        {
+            "dataPath": "params_shard_220.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.4.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cfbd084e886f15489f9dc8d678fe951c"
+        },
+        {
+            "dataPath": "params_shard_221.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.5.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cc997aa41b99ec4565ea555c0425716c"
+        },
+        {
+            "dataPath": "params_shard_222.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.5.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a2e52d44ccb0af99e263c52f8311b637"
+        },
+        {
+            "dataPath": "params_shard_223.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.5.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a97aeeadb978699d5dd32ee37d4a3a2e"
+        },
+        {
+            "dataPath": "params_shard_224.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.5.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "495cf3c9e5e2dd0c432e9e596cf1753a"
+        },
+        {
+            "dataPath": "params_shard_225.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.5.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c8a5be97170c65cf28cb30134ed801b7"
+        },
+        {
+            "dataPath": "params_shard_226.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.6.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fd5608dcad1fd12074aa07db3581cd7a"
+        },
+        {
+            "dataPath": "params_shard_227.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.4.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.4.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.5.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.5.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.5.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.5.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.5.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "921dc1bb85212b4f33d7076c1dabbc4d"
+        },
+        {
+            "dataPath": "params_shard_228.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.6.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ec05ca57c87e9d31dc24ad29c9453c60"
+        },
+        {
+            "dataPath": "params_shard_229.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.6.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4dae97fa6f51cbb62dcbd846d6020507"
+        },
+        {
+            "dataPath": "params_shard_230.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.6.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b14ff8a48f45923a930f8460dfd93b43"
+        },
+        {
+            "dataPath": "params_shard_231.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.6.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7a038ec935b25df77bac383fe0d6e7fb"
+        },
+        {
+            "dataPath": "params_shard_232.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.41.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bfa639fb061002c73aa16d0ec2d8148a"
+        },
+        {
+            "dataPath": "params_shard_233.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.42.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "89facc2ab8b6d91758d8169b82af99e8"
+        },
+        {
+            "dataPath": "params_shard_234.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.6.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.6.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.6.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.41.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.41.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.41.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31068160
+                },
+                {
+                    "name": "model.layers.42.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31084544
+                }
+            ],
+            "md5sum": "e07e25666832594dc3c2ac7d3cf2c14c"
+        },
+        {
+            "dataPath": "params_shard_235.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.42.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b76951c801f7c3e9c92f2fb58381da74"
+        },
+        {
+            "dataPath": "params_shard_236.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.42.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "adb8d11ec2abf138e09227717e9bfbf7"
+        },
+        {
+            "dataPath": "params_shard_237.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.42.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ca54b0f6572506729152bd15fcf1f305"
+        },
+        {
+            "dataPath": "params_shard_238.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.42.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e77bd8b5180b98614095c87fde69887c"
+        },
+        {
+            "dataPath": "params_shard_239.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.43.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1312b909da77cc8c354ea8302637ccec"
+        },
+        {
+            "dataPath": "params_shard_240.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.43.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "68abd564e4139d310dbac219e038d6ea"
+        },
+        {
+            "dataPath": "params_shard_241.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.43.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "15fbc908219c512a3dd57956a6665c4b"
+        },
+        {
+            "dataPath": "params_shard_242.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.43.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2de33a1975619791f537e96877b50515"
+        },
+        {
+            "dataPath": "params_shard_243.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.42.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.42.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.42.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.42.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.43.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.43.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.43.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31084544
+                }
+            ],
+            "md5sum": "0d511010bdee1a9c40cdc91301b4ae0a"
+        },
+        {
+            "dataPath": "params_shard_244.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.43.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.43.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "47533aed750b1991fd6714e8c46b7abc"
+        },
+        {
+            "dataPath": "params_shard_245.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.44.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9c253f6455374958e0478f03351ed6d5"
+        },
+        {
+            "dataPath": "params_shard_246.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.44.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "dd4ace0c00d614dfda4b6180ede3f9a7"
+        },
+        {
+            "dataPath": "params_shard_247.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.44.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a725fa8fba219730153b4484edaa9e09"
+        },
+        {
+            "dataPath": "params_shard_248.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.44.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "09d4a3f092e07ead47f5827e3dd47cb7"
+        },
+        {
+            "dataPath": "params_shard_249.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.44.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "27f6f9f65b73753b626a8f1221327d84"
+        },
+        {
+            "dataPath": "params_shard_250.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.45.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "30242e9d11ea1276f4410baa4e945130"
+        },
+        {
+            "dataPath": "params_shard_251.bin",
+            "format": "raw-shard",
+            "nbytes": 22712320,
+            "records": [
+                {
+                    "name": "model.layers.43.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.44.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.44.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 7557120
+                },
+                {
+                    "name": "model.layers.44.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 10915840
+                },
+                {
+                    "name": "model.layers.44.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 10932224
+                },
+                {
+                    "name": "model.layers.44.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22679552
+                },
+                {
+                    "name": "model.layers.45.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22695936
+                }
+            ],
+            "md5sum": "ed4075e3ef5d57707c68912a0b70239e"
+        },
+        {
+            "dataPath": "params_shard_252.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.45.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "84a2ac473cb4c7c4dd167866428729e8"
+        },
+        {
+            "dataPath": "params_shard_253.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.45.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "16160f789c9ceabb4ece069379a36274"
+        },
+        {
+            "dataPath": "params_shard_254.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.45.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d6067261615ebd915b196a04d4398e33"
+        },
+        {
+            "dataPath": "params_shard_255.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.45.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5c128bd46b166498c5031525c66d5862"
+        },
+        {
+            "dataPath": "params_shard_256.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.46.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a1f5eadbfdd1fe18559f637d8f1aa256"
+        },
+        {
+            "dataPath": "params_shard_257.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.46.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "88d6f149cd193791484533c1b85088e4"
+        },
+        {
+            "dataPath": "params_shard_258.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.46.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a270d91f5ae1272f04b015eb1f6ea673"
+        },
+        {
+            "dataPath": "params_shard_259.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.46.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2934017bb7a90fab2b16850109050561"
+        },
+        {
+            "dataPath": "params_shard_260.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.45.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.45.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.45.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.45.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.46.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19320832
+                }
+            ],
+            "md5sum": "4a890c3e9d70b1f084bbf36853452aed"
+        },
+        {
+            "dataPath": "params_shard_261.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.46.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.46.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "9d0b2f4931144f42c982479647bfc6da"
+        },
+        {
+            "dataPath": "params_shard_262.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.47.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d82c682c041f4935a926a78dbd2c2091"
+        },
+        {
+            "dataPath": "params_shard_263.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.47.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e214f2b46815db34cd6e3a2edbf69312"
+        },
+        {
+            "dataPath": "params_shard_264.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.47.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "da8e7a9ade09da252a3abac74fb44b0c"
+        },
+        {
+            "dataPath": "params_shard_265.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.47.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2725ca949403fc23499d62bd9af6c7da"
+        },
+        {
+            "dataPath": "params_shard_266.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.47.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c03a6ecf51bb4fa524eab183070648b6"
+        },
+        {
+            "dataPath": "params_shard_267.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.48.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "33e7a372f749d6432596f7c09b541146"
+        },
+        {
+            "dataPath": "params_shard_268.bin",
+            "format": "raw-shard",
+            "nbytes": 22745088,
+            "records": [
+                {
+                    "name": "model.layers.46.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.46.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.46.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.47.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3391488
+                },
+                {
+                    "name": "model.layers.47.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3407872
+                },
+                {
+                    "name": "model.layers.47.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15155200
+                },
+                {
+                    "name": "model.layers.47.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15171584
+                },
+                {
+                    "name": "model.layers.47.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19369984
+                },
+                {
+                    "name": "model.layers.48.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22728704
+                }
+            ],
+            "md5sum": "e9eb4f4b2318e9e0b25a9937b8a8c278"
+        },
+        {
+            "dataPath": "params_shard_269.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.48.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "47b8275ed6772e5630d620f47d0acf43"
+        },
+        {
+            "dataPath": "params_shard_270.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.48.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b5f9386eb91c9fe0d25f70c40411c618"
+        },
+        {
+            "dataPath": "params_shard_271.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.48.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b6be3511c4950ede9f6aeded99d4799e"
+        },
+        {
+            "dataPath": "params_shard_272.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.48.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bcc463bedecc2ae1945abfcb854974ff"
+        },
+        {
+            "dataPath": "params_shard_273.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.49.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e3435e3b798077f5b8c433bf1e247f91"
+        },
+        {
+            "dataPath": "params_shard_274.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.49.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6a465a0298d7e454d42a68b42f2b419b"
+        },
+        {
+            "dataPath": "params_shard_275.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.49.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "80e8fabc154fe66162d997cc8699477c"
+        },
+        {
+            "dataPath": "params_shard_276.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.49.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "deeec73b528e2e43f0f84f331683df57"
+        },
+        {
+            "dataPath": "params_shard_277.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.49.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5761c710d374cdbd28d399972765cc2a"
+        },
+        {
+            "dataPath": "params_shard_278.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.48.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.48.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.48.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.48.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.49.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.49.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.49.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "8763fcf096ba89fc2cc5fcf833b12b26"
+        },
+        {
+            "dataPath": "params_shard_279.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.50.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fadc81593147d42e8f66fa7a6a3e0fd6"
+        },
+        {
+            "dataPath": "params_shard_280.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.50.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b652ea2cde01590c05e659a3b206779f"
+        },
+        {
+            "dataPath": "params_shard_281.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.50.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d979213c44db0b3b3c3a3dd619dff9f1"
+        },
+        {
+            "dataPath": "params_shard_282.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.50.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "547c9d5059b67ce372f442ee5638c1cb"
+        },
+        {
+            "dataPath": "params_shard_283.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.50.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7561f49477b4b0749b3822552a7dd059"
+        },
+        {
+            "dataPath": "params_shard_284.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.51.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "51331e8345c9fb285dfc2a17d948cb33"
+        },
+        {
+            "dataPath": "params_shard_285.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.49.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.49.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.50.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.50.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.50.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.50.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.50.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.51.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "859051a597a79c0f3eda20de4a2f9782"
+        },
+        {
+            "dataPath": "params_shard_286.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.51.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fe48e663b2ac8edc436064ebe9415947"
+        },
+        {
+            "dataPath": "params_shard_287.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.51.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b8766f4760aee96c4d3829de01ba5636"
+        },
+        {
+            "dataPath": "params_shard_288.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.51.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ffd390a68e58cde53a6d40a0a20118a5"
+        },
+        {
+            "dataPath": "params_shard_289.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.51.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bacdbfee95562c0cd71e73ef0651d280"
+        },
+        {
+            "dataPath": "params_shard_290.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.52.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bec410229303031ca640e235322c3f51"
+        },
+        {
+            "dataPath": "params_shard_291.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.52.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e6e9974ea10d06bbf32b171546e931bb"
+        },
+        {
+            "dataPath": "params_shard_292.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.52.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d4ad61786afc7b201a6f889e37243ef2"
+        },
+        {
+            "dataPath": "params_shard_293.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.51.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.51.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.51.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.51.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.52.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.52.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.52.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "0eafde6c7c3d5416bcf0effd9baa783d"
+        },
+        {
+            "dataPath": "params_shard_294.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.52.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9cc7f705a609cbcf35fa91f7a0df3e3b"
+        },
+        {
+            "dataPath": "params_shard_295.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.52.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "54e688b9b7473e6ea94b53ac2677f82d"
+        },
+        {
+            "dataPath": "params_shard_296.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.53.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "140633d444f48fa9f8f0c89cc7fcfb9b"
+        },
+        {
+            "dataPath": "params_shard_297.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.53.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "692a2682403fb8a6c17136f03f7628ea"
+        },
+        {
+            "dataPath": "params_shard_298.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.53.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "20d07a89ee21569df6fd7ac87a6ae547"
+        },
+        {
+            "dataPath": "params_shard_299.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.53.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6a6c619bc7f546a4229260b42f92e8e6"
+        },
+        {
+            "dataPath": "params_shard_300.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.53.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7585c77c38db75665cb595da9f0e0ccf"
+        },
+        {
+            "dataPath": "params_shard_301.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.54.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0ab10ed3d7c00d79918cc1dea54ec7a7"
+        },
+        {
+            "dataPath": "params_shard_302.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.52.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.52.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.53.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.53.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.53.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.53.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.53.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "876be4c35f92d10ae663b99f319765d6"
+        },
+        {
+            "dataPath": "params_shard_303.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.54.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f1cb76ddd5a66e2bce517fee6abd34bc"
+        },
+        {
+            "dataPath": "params_shard_304.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.54.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f9018379eb03267c3af51c3852539a26"
+        },
+        {
+            "dataPath": "params_shard_305.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.54.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1c99be7ce6411f6c3bacdd0e2345f1aa"
+        },
+        {
+            "dataPath": "params_shard_306.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.54.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "215d512a808dbf937544fefd0e14ea53"
+        },
+        {
+            "dataPath": "params_shard_307.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.55.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0dd1e84589ae8c384ca6f3e34490f319"
+        },
+        {
+            "dataPath": "params_shard_308.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.55.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "386432ec87ea1d8d6b03481f9fe2249a"
+        },
+        {
+            "dataPath": "params_shard_309.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.55.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "03ef641939c9eb442bed94cc97ceb2fb"
+        },
+        {
+            "dataPath": "params_shard_310.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.55.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b06c0687ba0035c364fc4273e08eb12e"
+        },
+        {
+            "dataPath": "params_shard_311.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.54.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.54.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.54.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.54.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.54.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.55.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.55.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.55.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "d2767407a7d55ca9a2dbce4988e67e70"
+        },
+        {
+            "dataPath": "params_shard_312.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.55.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.55.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "8babe01b87eb90fa6698c7f866217b9e"
+        },
+        {
+            "dataPath": "params_shard_313.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.56.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "60b056264a5825dc90200a0d526d21ec"
+        },
+        {
+            "dataPath": "params_shard_314.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.56.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3059f4e668d4e9207240c0514ad207df"
+        },
+        {
+            "dataPath": "params_shard_315.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.56.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e09ce9bae1c4dbb75be8674a3559e701"
+        },
+        {
+            "dataPath": "params_shard_316.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.56.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "75edea55c3136f4d5d24a26a455bb4a3"
+        },
+        {
+            "dataPath": "params_shard_317.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.56.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2455a9d175a880b705491e5d437d969f"
+        },
+        {
+            "dataPath": "params_shard_318.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.57.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a515c69e75782123b7d78a34d23b93fb"
+        },
+        {
+            "dataPath": "params_shard_319.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.57.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9804936a1a8edbadc12ed61d1e8d32f8"
+        },
+        {
+            "dataPath": "params_shard_320.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.57.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cb907bf7356082231312818beb48d11c"
+        },
+        {
+            "dataPath": "params_shard_321.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.57.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "81a717150ea8665f9dc8d2bb9d28e535"
+        },
+        {
+            "dataPath": "params_shard_322.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.57.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "70617a61a5294dd40fc1292b61f21daf"
+        },
+        {
+            "dataPath": "params_shard_323.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.55.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.56.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.56.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.56.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.56.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.56.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.57.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.57.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.57.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "a919a948223bb961a7b64a82812928f3"
+        },
+        {
+            "dataPath": "params_shard_324.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.58.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e6bb46946fe07c9dfa924f840444320a"
+        },
+        {
+            "dataPath": "params_shard_325.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.58.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ba2b13163fb9b20297d0dfb881206dee"
+        },
+        {
+            "dataPath": "params_shard_326.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.58.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6c459d3ccbfce4a61ca0ef4a4aee9143"
+        },
+        {
+            "dataPath": "params_shard_327.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.58.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "545ad0ffafd4a119569227d2f88f2179"
+        },
+        {
+            "dataPath": "params_shard_328.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.58.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "aa0a409967b1186be9bb6c8edcb5a8eb"
+        },
+        {
+            "dataPath": "params_shard_329.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.59.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8607b1c14ea16fa889d3eec88e3cd3bc"
+        },
+        {
+            "dataPath": "params_shard_330.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.57.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.57.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.58.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.58.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.58.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.58.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.58.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.59.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "3cfffddb03d4916580d78990951bd91b"
+        },
+        {
+            "dataPath": "params_shard_331.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.59.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a1fdef211eed81a2d79e0343ffff5920"
+        },
+        {
+            "dataPath": "params_shard_332.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.59.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1d2d23cb2c2cf08590ec689ee9e9cd2a"
+        },
+        {
+            "dataPath": "params_shard_333.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.59.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "45565b546057082f06b66129bc32c6ae"
+        },
+        {
+            "dataPath": "params_shard_334.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.59.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "410b6888840b36d9059782d9f6781030"
+        },
+        {
+            "dataPath": "params_shard_335.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.60.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8014725d04e10c811863c0752c1f741f"
+        },
+        {
+            "dataPath": "params_shard_336.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.60.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a5ffd96d232511039a018314c0d26db4"
+        },
+        {
+            "dataPath": "params_shard_337.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.7.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f98fe84647968903ec1c0a74e7072f59"
+        },
+        {
+            "dataPath": "params_shard_338.bin",
+            "format": "raw-shard",
+            "nbytes": 26927104,
+            "records": [
+                {
+                    "name": "model.layers.59.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.59.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.59.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.59.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.60.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.60.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.6.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                },
+                {
+                    "name": "model.layers.6.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.7.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26910720
+                }
+            ],
+            "md5sum": "bf3bf386663d0ca4be6b984788989520"
+        },
+        {
+            "dataPath": "params_shard_339.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.7.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "047ca6db4442e1c0c49e84595aec1ddb"
+        },
+        {
+            "dataPath": "params_shard_340.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.7.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ae1187c2041ed5aa467283e3c3e54a7b"
+        },
+        {
+            "dataPath": "params_shard_341.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.7.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "52ae61c4e46be7abb8a916d958032d68"
+        },
+        {
+            "dataPath": "params_shard_342.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.7.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c0a8da3dece37ef53794268f81a9180c"
+        },
+        {
+            "dataPath": "params_shard_343.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.8.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2134f1042f04fb87a5784aa04a17c6b4"
+        },
+        {
+            "dataPath": "params_shard_344.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.8.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "958558d8655376d49d55f61800ef0d0a"
+        },
+        {
+            "dataPath": "params_shard_345.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.8.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "02adeeed350bbb1c61da8d33e148d863"
+        },
+        {
+            "dataPath": "params_shard_346.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.8.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "04f54c18987190e6a04dfafc16baa038"
+        },
+        {
+            "dataPath": "params_shard_347.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.7.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.7.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.7.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.7.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.8.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.8.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.8.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31084544
+                }
+            ],
+            "md5sum": "8b51e8e7dbcf1a4070101a585874878f"
+        },
+        {
+            "dataPath": "params_shard_348.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.8.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.8.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "c7066f2f90ff0ecbeb75fe3f4906efe1"
+        },
+        {
+            "dataPath": "params_shard_349.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.9.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "d91a602ed714850d69bbd590eeab9283"
+        },
+        {
+            "dataPath": "params_shard_350.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.9.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1535b482f4afe55f8c7ef9ca9a18cfda"
+        },
+        {
+            "dataPath": "params_shard_351.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.60.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "063de67e77c050634f12152bb0313d4c"
+        },
+        {
+            "dataPath": "params_shard_352.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.60.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c1c6f8adb77a26fa8c93adc337e45807"
+        },
+        {
+            "dataPath": "params_shard_353.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.60.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bd2102f76399f4f885f52dad491e0e97"
+        },
+        {
+            "dataPath": "params_shard_354.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.61.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "32fcaae3e9f73b5d6066aef120ddd169"
+        },
+        {
+            "dataPath": "params_shard_355.bin",
+            "format": "raw-shard",
+            "nbytes": 22712320,
+            "records": [
+                {
+                    "name": "model.layers.8.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.9.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.9.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 7557120
+                },
+                {
+                    "name": "model.layers.60.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 10915840
+                },
+                {
+                    "name": "model.layers.60.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 10932224
+                },
+                {
+                    "name": "model.layers.60.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22679552
+                },
+                {
+                    "name": "model.layers.61.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22695936
+                }
+            ],
+            "md5sum": "0f61eb3d55343e44b0cade19b6cc1692"
+        },
+        {
+            "dataPath": "params_shard_356.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.61.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bbad849629d04b91cc704e8a0f515447"
+        },
+        {
+            "dataPath": "params_shard_357.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.61.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cca878d6878de6ea4c96dc1438c7489c"
+        },
+        {
+            "dataPath": "params_shard_358.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.61.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5a7466885345100ea49946543f874d94"
+        },
+        {
+            "dataPath": "params_shard_359.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.61.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b182b156b48cddf64bfd1175341f7ff8"
+        },
+        {
+            "dataPath": "params_shard_360.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.62.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "77368db11d0f6fcb5d8c01fce6851221"
+        },
+        {
+            "dataPath": "params_shard_361.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.62.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "89f5055d7ed3cfe3cd730c6ee313b7b1"
+        },
+        {
+            "dataPath": "params_shard_362.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.62.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1e74c4ca24bde9a37a98d388422cd452"
+        },
+        {
+            "dataPath": "params_shard_363.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.62.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ada3dd95633f143f2c94250614d9bedc"
+        },
+        {
+            "dataPath": "params_shard_364.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.61.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.61.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.61.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.61.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.62.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19320832
+                }
+            ],
+            "md5sum": "709576fd70410ce7819ba5891ed2103b"
+        },
+        {
+            "dataPath": "params_shard_365.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.62.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.62.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "100fe9f0d2d3fa4ce435287e5e49d4c6"
+        },
+        {
+            "dataPath": "params_shard_366.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.63.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a940e118654ad9b73b99ecd5a6383a89"
+        },
+        {
+            "dataPath": "params_shard_367.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.63.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "66c3f21d12026b7d3467694c27338a1f"
+        },
+        {
+            "dataPath": "params_shard_368.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.63.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4e49b844cb2de448db112349d04c7d67"
+        },
+        {
+            "dataPath": "params_shard_369.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.63.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cf4d5c2e2dc977b0a7be1785c6408107"
+        },
+        {
+            "dataPath": "params_shard_370.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.63.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "60be79aacf67944ece7bde80d8b9e5d5"
+        },
+        {
+            "dataPath": "params_shard_371.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.64.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "17852749eb8951f3cecad440636ae8e6"
+        },
+        {
+            "dataPath": "params_shard_372.bin",
+            "format": "raw-shard",
+            "nbytes": 22745088,
+            "records": [
+                {
+                    "name": "model.layers.62.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.62.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.62.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.63.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3391488
+                },
+                {
+                    "name": "model.layers.63.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3407872
+                },
+                {
+                    "name": "model.layers.63.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15155200
+                },
+                {
+                    "name": "model.layers.63.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15171584
+                },
+                {
+                    "name": "model.layers.63.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19369984
+                },
+                {
+                    "name": "model.layers.64.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 22728704
+                }
+            ],
+            "md5sum": "549875ebe4fa06238c2ebc54d2027737"
+        },
+        {
+            "dataPath": "params_shard_373.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.64.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ebd952b644c1ff703ba15a4f88040366"
+        },
+        {
+            "dataPath": "params_shard_374.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.64.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3d514be256414b38c6478e7043c21bfb"
+        },
+        {
+            "dataPath": "params_shard_375.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.64.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6a443e55446132df925b167be445980f"
+        },
+        {
+            "dataPath": "params_shard_376.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.64.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3ffc86459d6293f801ada07106951fa9"
+        },
+        {
+            "dataPath": "params_shard_377.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.65.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "71f4e26f700f38a47e0008df7f978394"
+        },
+        {
+            "dataPath": "params_shard_378.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.65.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "0aa3b2070e1ba8f3ae760b4231d8e7ad"
+        },
+        {
+            "dataPath": "params_shard_379.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.65.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f5c8fbdaa49d8ca3e7318df7cbad6671"
+        },
+        {
+            "dataPath": "params_shard_380.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.65.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ab376176dda28e9fad5411a7286004c2"
+        },
+        {
+            "dataPath": "params_shard_381.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.65.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5147f0efb2a419393f3bcea23fbdda62"
+        },
+        {
+            "dataPath": "params_shard_382.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.64.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.64.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.64.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.64.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.65.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.65.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.65.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "f760c8704c0b0df52abd06049b7f9631"
+        },
+        {
+            "dataPath": "params_shard_383.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.66.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "24ee1adb7dac5f4a5bebd15ca73c552d"
+        },
+        {
+            "dataPath": "params_shard_384.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.66.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "122dfd389b9ec817c03a5c9cce9f965e"
+        },
+        {
+            "dataPath": "params_shard_385.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.66.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "170d2479b81e7af7d299f328417f10f9"
+        },
+        {
+            "dataPath": "params_shard_386.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.66.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3fa13457f601c2b120e05ab91a430a76"
+        },
+        {
+            "dataPath": "params_shard_387.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.66.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fb6c1a37f33f30e199c40cc43631073e"
+        },
+        {
+            "dataPath": "params_shard_388.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.67.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c9777715b880e586c7232ece24ad136c"
+        },
+        {
+            "dataPath": "params_shard_389.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.65.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.65.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.66.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.66.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.66.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.66.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.66.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.67.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "b1494fd5962e616b8e3f4bb0bb80726a"
+        },
+        {
+            "dataPath": "params_shard_390.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.67.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "42257b61690f58e3be063851b7faae9a"
+        },
+        {
+            "dataPath": "params_shard_391.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.67.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3d60cd9e2eeba70fa09097db03c80370"
+        },
+        {
+            "dataPath": "params_shard_392.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.67.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8a848f299681353b084c6106f7cd54db"
+        },
+        {
+            "dataPath": "params_shard_393.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.67.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b50e54de2d4c9a3309b19aac071eb050"
+        },
+        {
+            "dataPath": "params_shard_394.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.68.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2014fcae2395837c48b0aef991bb5f9e"
+        },
+        {
+            "dataPath": "params_shard_395.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.68.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "3f355cc6977f3eab6ab5e5feeb2337e5"
+        },
+        {
+            "dataPath": "params_shard_396.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.68.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9a42d0a0d3c615af0ab551544d70ba58"
+        },
+        {
+            "dataPath": "params_shard_397.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.67.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.67.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.67.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.67.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.68.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.68.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.68.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "6a52bcb76c37f486d25c8aa1d1b23e03"
+        },
+        {
+            "dataPath": "params_shard_398.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.68.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bde2ee6fced44ac3a052d6e8a16c5316"
+        },
+        {
+            "dataPath": "params_shard_399.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.68.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "cbb2b0a20b1d5c07d72ecaee503a1ed2"
+        },
+        {
+            "dataPath": "params_shard_400.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.69.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7848457d46172531e7d363ee9f9e755c"
+        },
+        {
+            "dataPath": "params_shard_401.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.69.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c10b36b430efa41d384a5da85c2fac7e"
+        },
+        {
+            "dataPath": "params_shard_402.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.69.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "793429547fb925487acdf8f15ccd90df"
+        },
+        {
+            "dataPath": "params_shard_403.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.69.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e1a99066671ae9eb99fb44d90d4a3600"
+        },
+        {
+            "dataPath": "params_shard_404.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.69.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "42f1ab09ecc306f4239338639d4f1f67"
+        },
+        {
+            "dataPath": "params_shard_405.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.70.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "e10a0af374090170da98774a6042e266"
+        },
+        {
+            "dataPath": "params_shard_406.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.68.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.68.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.69.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.69.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.69.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.69.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.69.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "e5c2acc47832a916476f30ebb8c65b70"
+        },
+        {
+            "dataPath": "params_shard_407.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.70.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f993d3474ae7214ef26aae4297f15667"
+        },
+        {
+            "dataPath": "params_shard_408.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.70.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "289a1acda65f35794a53a524bad483cf"
+        },
+        {
+            "dataPath": "params_shard_409.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.70.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1375d9202b345a1ee306be456a983db8"
+        },
+        {
+            "dataPath": "params_shard_410.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.70.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c947459666c078e5ee583c0e117091ec"
+        },
+        {
+            "dataPath": "params_shard_411.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.71.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "248a98edc814d222751eda3367b32c55"
+        },
+        {
+            "dataPath": "params_shard_412.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.71.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "9e89251a5341e524d813a66d14eaf2db"
+        },
+        {
+            "dataPath": "params_shard_413.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.71.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ee858778e48f935339627b702e766978"
+        },
+        {
+            "dataPath": "params_shard_414.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.71.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "8d1ca7b9b6b66b3e294df43a2520cc97"
+        },
+        {
+            "dataPath": "params_shard_415.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.70.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.70.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.70.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                },
+                {
+                    "name": "model.layers.70.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19304448
+                },
+                {
+                    "name": "model.layers.70.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.71.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.71.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 19353600
+                },
+                {
+                    "name": "model.layers.71.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "6cff4a1083971f10b9f1bc4ce8f15603"
+        },
+        {
+            "dataPath": "params_shard_416.bin",
+            "format": "raw-shard",
+            "nbytes": 31068160,
+            "records": [
+                {
+                    "name": "model.layers.71.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.71.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 4198400
+                }
+            ],
+            "md5sum": "9aafca48ed25d656e13dbe7902c04bcc"
+        },
+        {
+            "dataPath": "params_shard_417.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.72.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f8344305dbdec46ef77c3a2e7d2f0558"
+        },
+        {
+            "dataPath": "params_shard_418.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.72.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "a452f830b6152bb66ecdddffbc27833c"
+        },
+        {
+            "dataPath": "params_shard_419.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.72.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "944e65712153e758d35063b9c6290f2f"
+        },
+        {
+            "dataPath": "params_shard_420.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.72.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "b7f0421a915fa7ddc1f5352aa52275d2"
+        },
+        {
+            "dataPath": "params_shard_421.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.72.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2996c40b6814fc6ca6b87ef3e7bc7e0a"
+        },
+        {
+            "dataPath": "params_shard_422.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.73.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fb5d5e9a82cdf253ede5476e87f9eca5"
+        },
+        {
+            "dataPath": "params_shard_423.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.73.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "6febc2b13501463b6ef9f1ff4b7cc650"
+        },
+        {
+            "dataPath": "params_shard_424.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.73.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "72db8f3e7ccfcdf8a918c045f933e9fd"
+        },
+        {
+            "dataPath": "params_shard_425.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.73.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "fccf98ef477e14d6be7d0bca0b8af383"
+        },
+        {
+            "dataPath": "params_shard_426.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.73.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "c3ba0e330a84e0b7e3d02aa589dad5e3"
+        },
+        {
+            "dataPath": "params_shard_427.bin",
+            "format": "raw-shard",
+            "nbytes": 30269440,
+            "records": [
+                {
+                    "name": "model.layers.71.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.72.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 3358720
+                },
+                {
+                    "name": "model.layers.72.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 3375104
+                },
+                {
+                    "name": "model.layers.72.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 15122432
+                },
+                {
+                    "name": "model.layers.72.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 15138816
+                },
+                {
+                    "name": "model.layers.72.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 19337216
+                },
+                {
+                    "name": "model.layers.73.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 22695936
+                },
+                {
+                    "name": "model.layers.73.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 26894336
+                },
+                {
+                    "name": "model.layers.73.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 30253056
+                }
+            ],
+            "md5sum": "0af1f7c2505f6252a35b7508ef764e79"
+        },
+        {
+            "dataPath": "params_shard_428.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.74.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "dee4bc77e0fa04a699c18c9074b309fa"
+        },
+        {
+            "dataPath": "params_shard_429.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.74.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "f85855f5aa93b95413af010fd0eda18b"
+        },
+        {
+            "dataPath": "params_shard_430.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.74.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "bfcd7435b3661df406aa2b5bc11f2903"
+        },
+        {
+            "dataPath": "params_shard_431.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.74.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "110918662785caeb3070d95eae67fcf3"
+        },
+        {
+            "dataPath": "params_shard_432.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.74.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "4483a339a6e6f6cb4396b2f88ffb83a5"
+        },
+        {
+            "dataPath": "params_shard_433.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.75.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ea2c540c65bf0643bb22c0479be325c6"
+        },
+        {
+            "dataPath": "params_shard_434.bin",
+            "format": "raw-shard",
+            "nbytes": 31117312,
+            "records": [
+                {
+                    "name": "model.layers.73.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.73.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.74.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.74.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.74.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.74.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.74.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                },
+                {
+                    "name": "model.layers.75.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 31100928
+                }
+            ],
+            "md5sum": "91f1f23793a5d0a7dd5115fe83d236ac"
+        },
+        {
+            "dataPath": "params_shard_435.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.75.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "14a7c91ceb3a579510125f80588df0be"
+        },
+        {
+            "dataPath": "params_shard_436.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.75.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "46c6b45a821f0c8ccef9d0bc75e257d4"
+        },
+        {
+            "dataPath": "params_shard_437.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.75.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "da0f3c66035f0f9acbda1bcddfceeb39"
+        },
+        {
+            "dataPath": "params_shard_438.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.75.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "57ddc53858c0ae334b556b25f7b22c7e"
+        },
+        {
+            "dataPath": "params_shard_439.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.76.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "aba30719035d9568b4688cf06ff90bd7"
+        },
+        {
+            "dataPath": "params_shard_440.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.76.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "03415a79b05594a0885ebb45aa7d1209"
+        },
+        {
+            "dataPath": "params_shard_441.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.76.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "5d575433b7c3ebd082d257fd50e3cb24"
+        },
+        {
+            "dataPath": "params_shard_442.bin",
+            "format": "raw-shard",
+            "nbytes": 26894336,
+            "records": [
+                {
+                    "name": "model.layers.75.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.75.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.75.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.75.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15962112
+                },
+                {
+                    "name": "model.layers.76.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 19320832
+                },
+                {
+                    "name": "model.layers.76.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 23519232
+                },
+                {
+                    "name": "model.layers.76.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 26877952
+                }
+            ],
+            "md5sum": "4f884d1a30ee4a39f29f7ddd3d651a15"
+        },
+        {
+            "dataPath": "params_shard_443.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.76.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "13a654dc708b7a89afe12f12abfc9d23"
+        },
+        {
+            "dataPath": "params_shard_444.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.76.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "39b1e316dcc208b8adfaf710a6fb7143"
+        },
+        {
+            "dataPath": "params_shard_445.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.77.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "2cd8a01d9c130440d3c13681916f42c3"
+        },
+        {
+            "dataPath": "params_shard_446.bin",
+            "format": "raw-shard",
+            "nbytes": 188088320,
+            "records": [
+                {
+                    "name": "model.layers.77.mlp.gate_up_proj.q_weight",
+                    "shape": [
+                        57344,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 188088320,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "ba110657e7f279e8289ae60e2c159b0f"
+        },
+        {
+            "dataPath": "params_shard_447.bin",
+            "format": "raw-shard",
+            "nbytes": 23511040,
+            "records": [
+                {
+                    "name": "model.layers.77.mlp.gate_up_proj.q_scale",
+                    "shape": [
+                        57344,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 23511040,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "080c0931525a6ad2f37faf0e69608ba6"
+        },
+        {
+            "dataPath": "params_shard_448.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.77.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "7604dd86e464d2d42b2697057d290997"
+        },
+        {
+            "dataPath": "params_shard_449.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.77.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "02bad9b8cd38c606d1e9532069f166f1"
+        },
+        {
+            "dataPath": "params_shard_450.bin",
+            "format": "raw-shard",
+            "nbytes": 93978624,
+            "records": [
+                {
+                    "name": "model.layers.78.mlp.down_proj.q_weight",
+                    "shape": [
+                        8192,
+                        2868
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 93978624,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "1a28e16d308fb7e11b69c11656768133"
+        },
+        {
+            "dataPath": "params_shard_451.bin",
+            "format": "raw-shard",
+            "nbytes": 31100928,
+            "records": [
+                {
+                    "name": "model.layers.76.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.76.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.77.input_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 11763712
+                },
+                {
+                    "name": "model.layers.77.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 11780096
+                },
+                {
+                    "name": "model.layers.77.post_attention_layernorm.weight",
+                    "shape": [
+                        8192
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 16384,
+                    "byteOffset": 23527424
+                },
+                {
+                    "name": "model.layers.77.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 23543808
+                },
+                {
+                    "name": "model.layers.77.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 27742208
+                }
+            ],
+            "md5sum": "c67f462f4811942f0a595937662ba569"
+        },
+        {
+            "dataPath": "params_shard_452.bin",
+            "format": "raw-shard",
+            "nbytes": 33587200,
+            "records": [
+                {
+                    "name": "model.layers.78.self_attn.qkv_proj.q_weight",
+                    "shape": [
+                        10240,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 33587200,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "39973ece34b8ed01a9a412a787930d9e"
+        },
+        {
+            "dataPath": "params_shard_453.bin",
+            "format": "raw-shard",
+            "nbytes": 26869760,
+            "records": [
+                {
+                    "name": "model.layers.78.self_attn.o_proj.q_weight",
+                    "shape": [
+                        8192,
+                        820
+                    ],
+                    "dtype": "uint32",
+                    "format": "f32-to-bf16",
+                    "nbytes": 26869760,
+                    "byteOffset": 0
+                }
+            ],
+            "md5sum": "29131681a3424c263a51e960453bf1ff"
+        },
+        {
+            "dataPath": "params_shard_454.bin",
+            "format": "raw-shard",
+            "nbytes": 19304448,
+            "records": [
+                {
+                    "name": "model.layers.78.mlp.down_proj.q_scale",
+                    "shape": [
+                        8192,
+                        717
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 11747328,
+                    "byteOffset": 0
+                },
+                {
+                    "name": "model.layers.78.self_attn.qkv_proj.q_scale",
+                    "shape": [
+                        10240,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 4198400,
+                    "byteOffset": 11747328
+                },
+                {
+                    "name": "model.layers.78.self_attn.o_proj.q_scale",
+                    "shape": [
+                        8192,
+                        205
+                    ],
+                    "dtype": "float16",
+                    "format": "f32-to-bf16",
+                    "nbytes": 3358720,
+                    "byteOffset": 15945728
+                }
+            ],
+            "md5sum": "fc160b5827af5203c37213e0f69d7fd3"
+        }
+    ]
+}
\ No newline at end of file
diff --git a/params_shard_0.bin b/params_shard_0.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cceaa57e6b5932e079016f91be4e5a51cd397a50
--- /dev/null
+++ b/params_shard_0.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b805894a9a5515f583cc583122e812b0fa932461ff3668bad69faa3867f5958e
+size 420679680
diff --git a/params_shard_1.bin b/params_shard_1.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e381ec00b9a404408d59e2b98a5d516d85b0cf6f
--- /dev/null
+++ b/params_shard_1.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24d34dc805cb16925b578b4518ec353d4e85a1b5b479335c32a1acb99ec7312
+size 52584960
diff --git a/params_shard_10.bin b/params_shard_10.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b5ebe3b5103b4c0572a9a29d74ae67fe79b6dc43
--- /dev/null
+++ b/params_shard_10.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d146d10de97542fcedf506353f2fcf36697050a69bcac34c77fd432414cdfef2
+size 52584960
diff --git a/params_shard_100.bin b/params_shard_100.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0f285fec2a6dcf40ce000be21611617bb2c30e97
--- /dev/null
+++ b/params_shard_100.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac1bff09949508a516e163d92619a45fb5221aeeebfbde9e4ca6852a9a81833
+size 23511040
diff --git a/params_shard_101.bin b/params_shard_101.bin
new file mode 100644
index 0000000000000000000000000000000000000000..11ca0f0422e377952f602b798d98c1fe6c3ced44
--- /dev/null
+++ b/params_shard_101.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931ece93508d9c808881f816c007b5a53c5a705a1c63849250e2711a00ab0e31
+size 93978624
diff --git a/params_shard_102.bin b/params_shard_102.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e9e2522f46b7d148cbc650402aec3ec0e94dae86
--- /dev/null
+++ b/params_shard_102.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74e0c66b2d1b5b3563ceffe1fd0d78e10448b0f96c690b1843953515f0bb871
+size 188088320
diff --git a/params_shard_103.bin b/params_shard_103.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ffe213ca90ad553ee84a471fc50c48748616b71
--- /dev/null
+++ b/params_shard_103.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2aa09ccc875790f520007e638eab1231532985a3155264c0ac90f295c256908
+size 23511040
diff --git a/params_shard_104.bin b/params_shard_104.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e79095b78b882c3cbe2cc887a7fb8fd31845907b
--- /dev/null
+++ b/params_shard_104.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dcda4fa2ad0a415e6cead6beac090b6aed555c9aa83a4300683032899adfa4
+size 33587200
diff --git a/params_shard_105.bin b/params_shard_105.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f2e2299a3809b4d983eb42481c1df31b392555c8
--- /dev/null
+++ b/params_shard_105.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731f7a2208fc5c0d2da3d41b8fe4c143ec206276972b2748ccdc14dfad6cb957
+size 26869760
diff --git a/params_shard_106.bin b/params_shard_106.bin
new file mode 100644
index 0000000000000000000000000000000000000000..01a7775391db559c2b8c6a568ca1f525bc955b0e
--- /dev/null
+++ b/params_shard_106.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70dec61286358f03e4d763d48a710066a926b09fe6d873384730bff2908db807
+size 93978624
diff --git a/params_shard_107.bin b/params_shard_107.bin
new file mode 100644
index 0000000000000000000000000000000000000000..180a0cb4c6bcb412df5ad702af110ccea1709d46
--- /dev/null
+++ b/params_shard_107.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6caaa3d0eb4ac6e88d21b9efeded9946b824dec1fc4db9d53226994c9267dbe9
+size 31100928
diff --git a/params_shard_108.bin b/params_shard_108.bin
new file mode 100644
index 0000000000000000000000000000000000000000..77535512a289515588582cc41bcf48736e61cdad
--- /dev/null
+++ b/params_shard_108.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cbaba959a198d419da382ef456dd4fed8c6e0a70918fe62fe66a52cca0c1a4
+size 188088320
diff --git a/params_shard_109.bin b/params_shard_109.bin
new file mode 100644
index 0000000000000000000000000000000000000000..69183e049e8ddd4e03f0bb6e451740ab7b1ed856
--- /dev/null
+++ b/params_shard_109.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91f273a66dd19a6bbfd4eff3295b1619227dd23b18962a8a1aa308245611eb0
+size 23511040
diff --git a/params_shard_11.bin b/params_shard_11.bin
new file mode 100644
index 0000000000000000000000000000000000000000..49f9533b31f3594aab445569ca5bd3c41f8a16d5
--- /dev/null
+++ b/params_shard_11.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff670a9edbe4663ab91a45e90dd7691cc1a5f97edf790b4075b8acb96ae6841d
+size 93978624
diff --git a/params_shard_110.bin b/params_shard_110.bin
new file mode 100644
index 0000000000000000000000000000000000000000..915f645d7a9dd391967161d698f2227d75f9f9ae
--- /dev/null
+++ b/params_shard_110.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167ae5c25fc05f221c96466b635d008a9f4b4bf7b12f1077faf15ef45e3cc035
+size 33587200
diff --git a/params_shard_111.bin b/params_shard_111.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7d48e67271df6b384e9ee7cc156c996bcd30ca7c
--- /dev/null
+++ b/params_shard_111.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ecb98e7fba29a360d6ac71a019f041a7644ae05cac7905e3c684858da22564
+size 26869760
diff --git a/params_shard_112.bin b/params_shard_112.bin
new file mode 100644
index 0000000000000000000000000000000000000000..274052ada4f82490d7d58c702e43a9a294d899a4
--- /dev/null
+++ b/params_shard_112.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49cb1df6e93637ef3b30a8b5977f7863cf4c920f6757ef98de22da830f293eb9
+size 93978624
diff --git a/params_shard_113.bin b/params_shard_113.bin
new file mode 100644
index 0000000000000000000000000000000000000000..edf9726a7b16646aab2e2d7148090ef1cabd567e
--- /dev/null
+++ b/params_shard_113.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daacffe310213cba6f3f4881116e172302694492f36343095fafa7950ecdb8b8
+size 188088320
diff --git a/params_shard_114.bin b/params_shard_114.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fda7756fb3e7289a44ee88ff9a46bb8ef71f293e
--- /dev/null
+++ b/params_shard_114.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492011af08a6ccf87f1ab648436ec47290a985a6416326fbbf0c26fa4f2bafc0
+size 23511040
diff --git a/params_shard_115.bin b/params_shard_115.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e822562ce2c1ba0246c951c341a3baf905300320
--- /dev/null
+++ b/params_shard_115.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1afc17922f18676bb7e091eaec4b2a9bb4252e45a1d203fddf609f99c044f1
+size 33587200
diff --git a/params_shard_116.bin b/params_shard_116.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3dd018de99a3415d440ede300c79fc8db26f69a0
--- /dev/null
+++ b/params_shard_116.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1fcbc9efa214e4271185bcfb0ad468054a24a8f8eb42375d65b1e7855ceaa1
+size 31117312
diff --git a/params_shard_117.bin b/params_shard_117.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2543e80210ebf4040469bd404326bd35f5d11a94
--- /dev/null
+++ b/params_shard_117.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50aabae8aa9466186ebc3363d0c9c8499d40851a503da34bf8ce8e3888c14f51
+size 31068160
diff --git a/params_shard_118.bin b/params_shard_118.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2702457f5bfc060274e9926bcab5bd33c9937bee
--- /dev/null
+++ b/params_shard_118.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d4d7329c45d58f135e0758824aa1d031f2ac8ef8d7019fb26c4f2d50680028
+size 93978624
diff --git a/params_shard_119.bin b/params_shard_119.bin
new file mode 100644
index 0000000000000000000000000000000000000000..39f1dfe38fb01cf1e3cd50a0a39d1c3041452478
--- /dev/null
+++ b/params_shard_119.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ca4d8eaed7951d76b6580ab27755fe8233f6a0a44525d261fef24ffecaa0f9
+size 188088320
diff --git a/params_shard_12.bin b/params_shard_12.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c067a4e85d8357b5ebabe2a011fba697444c31c2
--- /dev/null
+++ b/params_shard_12.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41d0677e249f3e9a339f6817d9526d9110924bdd1e26a59afc7d2aa7bc0ccdd
+size 188088320
diff --git a/params_shard_120.bin b/params_shard_120.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8050995a521fbaba2b40d270716d57d82c601078
--- /dev/null
+++ b/params_shard_120.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcda87e7876a280c50259bc54bd277438f34cebc7f3bbb8a14871ad9f11dad46
+size 23511040
diff --git a/params_shard_121.bin b/params_shard_121.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d8317867f1601ee50499c2643e697acf8c732e89
--- /dev/null
+++ b/params_shard_121.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116605a2f258191978e71aa38df8f3dce1f88ddbfe7e498d908d4a299d4ff8f4
+size 33587200
diff --git a/params_shard_122.bin b/params_shard_122.bin
new file mode 100644
index 0000000000000000000000000000000000000000..106f56dca06becf47518231691368e11f73f671e
--- /dev/null
+++ b/params_shard_122.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c0716a4fa9df321eb015a34b5bcd61cb4814bf8e040b55c0cfed9760dbeebc
+size 26869760
diff --git a/params_shard_123.bin b/params_shard_123.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a3b44c73315b1d5c84f56d0483e9dce8d13ef11b
--- /dev/null
+++ b/params_shard_123.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a0f46dfd7cbc0fa542470bc5f22a353f82b86cdd30c4b232c8ecaedfa2a81d
+size 188088320
diff --git a/params_shard_124.bin b/params_shard_124.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7fc0567e73ae4e31698081d103c9372fb8da96d3
--- /dev/null
+++ b/params_shard_124.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c9c58317d67fd839608acbcc5f789555e1e94cbfd9a935f9701e265e1263fd
+size 23511040
diff --git a/params_shard_125.bin b/params_shard_125.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6d52c5488a3b26e38e3de6444515bb33c4df3dfd
--- /dev/null
+++ b/params_shard_125.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea5a5ebf7dc4c6321176e44a5827faec71df9f94da2122ebc5518399ec6d268
+size 33587200
diff --git a/params_shard_126.bin b/params_shard_126.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1e2aed5867c7b3eef60e8819250954a05e710251
--- /dev/null
+++ b/params_shard_126.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6935a88cba775a94b63ff4a50f30d6fffce7ea563209bd29edc858cae720bc7
+size 26869760
diff --git a/params_shard_127.bin b/params_shard_127.bin
new file mode 100644
index 0000000000000000000000000000000000000000..32b93e8402313bcfa2e4a64b48a7c0dbe7b75db9
--- /dev/null
+++ b/params_shard_127.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7800ee97386028cddd950e6c2993d7c5b09037ac902700874cbe1a9fc2ba4994
+size 93978624
diff --git a/params_shard_128.bin b/params_shard_128.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7ebc4dcccbb6b998eadd6ccf7a53404c50c64dc3
--- /dev/null
+++ b/params_shard_128.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024a0fc7b25d8737712a50c16be37e355c35a689ceaf2dc68ec7fe41215fe061
+size 30269440
diff --git a/params_shard_129.bin b/params_shard_129.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d81c3b13f1b581f7896d91d442f12949c494089
--- /dev/null
+++ b/params_shard_129.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa66637c4e2ad1de77837d2ee5149a46c8858342f6180b7a36dd3b9074949a7
+size 93978624
diff --git a/params_shard_13.bin b/params_shard_13.bin
new file mode 100644
index 0000000000000000000000000000000000000000..33ba0ed750f23f9d018200a5137179656691c28f
--- /dev/null
+++ b/params_shard_13.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669c00ebe28ea689370d6698e52e16cb6bf2b514d1cf6fe3d49ab8fc312d05db
+size 23511040
diff --git a/params_shard_130.bin b/params_shard_130.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5da98b8fd7face473a0df14bcd5119b5cd95286f
--- /dev/null
+++ b/params_shard_130.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2746d0ad30eaccc95d207bdc3243f56266bb4b6db201164d602de56a5e12738
+size 188088320
diff --git a/params_shard_131.bin b/params_shard_131.bin
new file mode 100644
index 0000000000000000000000000000000000000000..530f45d0a322491355bfad2cc17c370a6507f2c8
--- /dev/null
+++ b/params_shard_131.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179afb3b2b9058450a8772ce8ef325473958c5fb0a857bb770a2ad24eb7944bd
+size 23511040
diff --git a/params_shard_132.bin b/params_shard_132.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0ebfdc529bf904c8810b0cbe730f6f90bdf66f28
--- /dev/null
+++ b/params_shard_132.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cc6e7e88c493630e2a21a84e8c4c1934b58af3d57a6fe85ca1c836b44542c9
+size 33587200
diff --git a/params_shard_133.bin b/params_shard_133.bin
new file mode 100644
index 0000000000000000000000000000000000000000..16a361911c18099e8ca37d4b8fea9d017dc55257
--- /dev/null
+++ b/params_shard_133.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2579ac07b6293db3aaa25c5e6c23944fd6cce7f1e79fb0f67499da77365e842e
+size 26869760
diff --git a/params_shard_134.bin b/params_shard_134.bin
new file mode 100644
index 0000000000000000000000000000000000000000..09544d57ce86d778446c7ab62564ce19836c83ec
--- /dev/null
+++ b/params_shard_134.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9b150493bcd925ffc7f8a391b89ebd92c8565016a4104f527307124e02e7f4
+size 93978624
diff --git a/params_shard_135.bin b/params_shard_135.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4848250fb6cd6b37f8b7a6a587bc93480c52499b
--- /dev/null
+++ b/params_shard_135.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c15353124c3c684446ec2f9e216b4e8ca0a9d09308b34032b87fae05233a20a1
+size 31117312
diff --git a/params_shard_136.bin b/params_shard_136.bin
new file mode 100644
index 0000000000000000000000000000000000000000..00c92e2a9ce24875eb2d1ff0ab2164d53c7177ee
--- /dev/null
+++ b/params_shard_136.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bb8f0d372dc64a51f051efa90026e645df9590966fdd0bec8767b3722b611d
+size 188088320
diff --git a/params_shard_137.bin b/params_shard_137.bin
new file mode 100644
index 0000000000000000000000000000000000000000..305c8a9de4455524bb0f0ed07b184443039b47a2
--- /dev/null
+++ b/params_shard_137.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ddef2dd949a3c28d4b4f2332eb9398efdce0b877315beb1f0f8c6627ed7d62
+size 23511040
diff --git a/params_shard_138.bin b/params_shard_138.bin
new file mode 100644
index 0000000000000000000000000000000000000000..95bf443483a553c74e672a2a41d8de764ad9b3a7
--- /dev/null
+++ b/params_shard_138.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224f16d4ae31c3e3a61b311640b16b8239ff6e9f08e07cfb62b3dc6435aff1c8
+size 33587200
diff --git a/params_shard_139.bin b/params_shard_139.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c7baa5e07c2316d69251d86fbac40a02d1be3cf2
--- /dev/null
+++ b/params_shard_139.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2558e90cf24c5e7bdbe0042244e187a38746fe696111a0d3bfe6e7d566f32c8f
+size 26869760
diff --git a/params_shard_14.bin b/params_shard_14.bin
new file mode 100644
index 0000000000000000000000000000000000000000..324fd519b5c714cb03a144617bdf794c0242f7e7
--- /dev/null
+++ b/params_shard_14.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6edcf5c4177f690fffb11674f0b0477deacbe6373f044fb91728c0dbb460bf5
+size 33587200
diff --git a/params_shard_140.bin b/params_shard_140.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3e639ed2d48d4d30eaa0429a5997d274062198db
--- /dev/null
+++ b/params_shard_140.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faa1d73792873a31f98d9492af83bf135e2046d65755440dcb5290ae53473cf
+size 33587200
diff --git a/params_shard_141.bin b/params_shard_141.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ea7f0afbdcc4a660cf40bd600d4c7aa2f021bcaf
--- /dev/null
+++ b/params_shard_141.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b05f41783039048fbf7679b51cb9e51368a8cf5f322ef58b53467ac7802681
+size 26869760
diff --git a/params_shard_142.bin b/params_shard_142.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a1ca95b782a79aad02c2f0f398bfcb7661d170d8
--- /dev/null
+++ b/params_shard_142.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1211d4e48081ac34e02be3b4d9b323055ce8fbb17932c57b77ce5f12cea380e9
+size 93978624
diff --git a/params_shard_143.bin b/params_shard_143.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9381d7790255c31b1e9843da6d787f2a00aa7e4b
--- /dev/null
+++ b/params_shard_143.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b659c8d5823d626dbfd23b34547ead6427b6e3b40a3180510a1cf69c49c71f55
+size 26894336
diff --git a/params_shard_144.bin b/params_shard_144.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7adb914fa8bbb340a243371eff49ee87bd2e72f4
--- /dev/null
+++ b/params_shard_144.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8961874b662a3a7f88226a49278ebd7307a07b6c0ce8d9fa0abc120ebf2f21fb
+size 188088320
diff --git a/params_shard_145.bin b/params_shard_145.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d20267d34ebe3dd3613321b1db3545ba68df46c2
--- /dev/null
+++ b/params_shard_145.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bca74af1fa27b65bad71f1c4b0cd8d35488aad69115e74248cb228906100273
+size 23511040
diff --git a/params_shard_146.bin b/params_shard_146.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1beeb5b8192025bbebb5fb39ecdaac9dc656cf9e
--- /dev/null
+++ b/params_shard_146.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7632326b0ceb966c79d60783636d8b2a95748858c002d8bb3a296153ef338a9b
+size 93978624
diff --git a/params_shard_147.bin b/params_shard_147.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0e4a62db1a2ac414437beda6f98b03b737f3d15f
--- /dev/null
+++ b/params_shard_147.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa639f5118ab3fd368177d477cba346ab7ad930fb2329626bb1a4e8d09414711
+size 188088320
diff --git a/params_shard_148.bin b/params_shard_148.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b6457478d112d5b5a262908d6038784d550afad
--- /dev/null
+++ b/params_shard_148.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac42ad470e85cae3cee83b2ee62b4f08403a4b6633936e4a5277f47675c8c4c
+size 23511040
diff --git a/params_shard_149.bin b/params_shard_149.bin
new file mode 100644
index 0000000000000000000000000000000000000000..91df36b36aeff8f78372cf528e79b94a3f7e30ac
--- /dev/null
+++ b/params_shard_149.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea789f5f45b2fac18e76afe58d4f53c8dc51bad538ee7c5321051f625c16b6e1
+size 33587200
diff --git a/params_shard_15.bin b/params_shard_15.bin
new file mode 100644
index 0000000000000000000000000000000000000000..268dd87d142f1a7c5d37d6586806088c98792330
--- /dev/null
+++ b/params_shard_15.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb95e1be0c9466415ea4bdb6a65b27b9816a3a75fd41bd3c2532da7bc4c961ef
+size 31117312
diff --git a/params_shard_150.bin b/params_shard_150.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3e127b91eebeca9b35fe2c0a6853502ad8327c0a
--- /dev/null
+++ b/params_shard_150.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2ccfbe59dff38737e6bf96c119f1a7bf33b340790cedd2aa8ec8c248c1a352
+size 26869760
diff --git a/params_shard_151.bin b/params_shard_151.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4734cacd6cf061e18ccfce9247d2de856735c509
--- /dev/null
+++ b/params_shard_151.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03dafc1d8ccc89ecdec92da67c482864afc0a3384bd0a75e674894f97d074361
+size 93978624
diff --git a/params_shard_152.bin b/params_shard_152.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c98ab288ca7c1d559c7bd59398efac35493b79da
--- /dev/null
+++ b/params_shard_152.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72f0a9c7949e97e6db51eb6acd80e5c4096129f68524d1a06622573b8e97baa
+size 31100928
diff --git a/params_shard_153.bin b/params_shard_153.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e6eee6d5e45e2b269d50a96b6bc81aa4409a664f
--- /dev/null
+++ b/params_shard_153.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7905c84ae10733c13ea680a669ddb63e9627e9bb9dbc4ef0c1c4e596b4f54243
+size 188088320
diff --git a/params_shard_154.bin b/params_shard_154.bin
new file mode 100644
index 0000000000000000000000000000000000000000..68c183c7eebe193b1b0d90eb931a087ebecae569
--- /dev/null
+++ b/params_shard_154.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4d8866586e7c1c0853d03eb1170d5e7cfd1754dbcb646edb48fb448b029702
+size 23511040
diff --git a/params_shard_155.bin b/params_shard_155.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e4306ed1ca7045379b47aff488440f8e1429bf53
--- /dev/null
+++ b/params_shard_155.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cab025e1d1cc7c0f3343d140a17b69f77ef689ee5c0a3b0d620ea24420f3b5
+size 33587200
diff --git a/params_shard_156.bin b/params_shard_156.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6bc6e0b9764932eee61d11c4515e3c4292ef7d4
--- /dev/null
+++ b/params_shard_156.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6566defd479028a77c35a033727b1f994cdeeababa428b251b3145e2eba16004
+size 26869760
diff --git a/params_shard_157.bin b/params_shard_157.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c933d7972057e09029dbccd29cf68340de9f6dcf
--- /dev/null
+++ b/params_shard_157.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4510fe55525dd246a0148e2633329b43293c38572c0dcb919bcd052a93656e6
+size 93978624
diff --git a/params_shard_158.bin b/params_shard_158.bin
new file mode 100644
index 0000000000000000000000000000000000000000..422ae66ee4b00d3e610eac021ddbff9bfe7dfb90
--- /dev/null
+++ b/params_shard_158.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e62b0906a704ef1989d73d9cd832a68c1d583d4d5314f8714808c6176aa27e8
+size 188088320
diff --git a/params_shard_159.bin b/params_shard_159.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a3ba9ba14ddb85d75a4878631431b9f6f85660ab
--- /dev/null
+++ b/params_shard_159.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9009a7b69633f0b2db4670ea50bc4ba7de2edeb7673705c2eda9faca72837f2
+size 23511040
diff --git a/params_shard_16.bin b/params_shard_16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f5a0bee80544169d703fadd6be0ad004dd445ba9
--- /dev/null
+++ b/params_shard_16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02db42c90dcc98af4bc21a28c5c48c118ea247b47b071a29e0d3aec38ddaf953
+size 31068160
diff --git a/params_shard_160.bin b/params_shard_160.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fe051d50b831acee6043b3027dba30d472729b33
--- /dev/null
+++ b/params_shard_160.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da34077ae5d1fd2b9624276bb160329d6d064137a7bda1e255e57b78ff2de7b
+size 33587200
diff --git a/params_shard_161.bin b/params_shard_161.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5b51dbdde0f411f24c541ae36942377f160882cc
--- /dev/null
+++ b/params_shard_161.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557a4ec53c87a8d7f9a5ac53e1c48d752a4cd13f1e7f8a4fa858a73c461c35d9
+size 31117312
diff --git a/params_shard_162.bin b/params_shard_162.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1fb1066128e6eb3cb592eda8db3e5758dafa92d3
--- /dev/null
+++ b/params_shard_162.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ab9f81390ddd926569da2b0a0e8fffb79e3459f2de708d82876a8363657915
+size 31068160
diff --git a/params_shard_163.bin b/params_shard_163.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d4c68e339c0ab9dd6fb478f71e1dff27628852de
--- /dev/null
+++ b/params_shard_163.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a4baaa5f1b65b39d99c7143c7042a63f4be701198fb9b753771fdd3b3130fb
+size 93978624
diff --git a/params_shard_164.bin b/params_shard_164.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a691556807e350ac84d26f26255840831ccc6d5d
--- /dev/null
+++ b/params_shard_164.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48aea7ac186fbb9aabc1a475a3d5276e10d0f62e19b0306989240b848ce4f693
+size 188088320
diff --git a/params_shard_165.bin b/params_shard_165.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c67e7d14a81b0f0a131e8a449659f56ca116680f
--- /dev/null
+++ b/params_shard_165.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5c7cdf6f27df81560af0680a4a9e0017fff763032c258b2ce24fe26b087df0
+size 23511040
diff --git a/params_shard_166.bin b/params_shard_166.bin
new file mode 100644
index 0000000000000000000000000000000000000000..639eeb50e679825a6fd3eee5621b030be63efb9b
--- /dev/null
+++ b/params_shard_166.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996498792588d12b43bb299275e7cc2b23d8246580b7782f9f2f1a406eea6ef3
+size 33587200
diff --git a/params_shard_167.bin b/params_shard_167.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d8a0143958cf8e6eb7e3a675df1058db2b6b16a2
--- /dev/null
+++ b/params_shard_167.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bccdcdb5fef147a07f85534b0bda6367607fbe45aa8f2eeff769c6de5f1c74
+size 26869760
diff --git a/params_shard_168.bin b/params_shard_168.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4d3f363a6b7aa77aa72a998502eae9dfd4caf71
--- /dev/null
+++ b/params_shard_168.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc7985b5cacca88573c161de86992309d2022f5ee356638f1bb6c176aa8e838
+size 188088320
diff --git a/params_shard_169.bin b/params_shard_169.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2204fbe16d518f46c88221745c28a0ee55635453
--- /dev/null
+++ b/params_shard_169.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ccc092e121b2ed5e7048a6440b426c45047b1c0d9e6bae465ee87e748b7a71
+size 23511040
diff --git a/params_shard_17.bin b/params_shard_17.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bfa2bb903253ae31f8b36ff4c52ea9ca774e9738
--- /dev/null
+++ b/params_shard_17.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4494e60a99ccff70702c617787561daf13da7d3d137848bc1c52da7d4153e43d
+size 188088320
diff --git a/params_shard_170.bin b/params_shard_170.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5e39d988cfa9dd2b8732f87d8403bb0b99d8291b
--- /dev/null
+++ b/params_shard_170.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a576c7e8611b2a4500f9f5c3988dabd9e43f1564504d8899fc6f3b62d213e1
+size 33587200
diff --git a/params_shard_171.bin b/params_shard_171.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bbd72158778c277001f5b30862a9f13f46e53a23
--- /dev/null
+++ b/params_shard_171.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82a355afdd01d52fd3f29d855092df95820c89450db1188787d9fb0c6f1c0cb
+size 26869760
diff --git a/params_shard_172.bin b/params_shard_172.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ca2184c2fcd789f5693905bb4a2cbd670c202958
--- /dev/null
+++ b/params_shard_172.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99801d3b92f16d625869a838f1874b21ca3b101a94082d2447132a57903322c5
+size 93978624
diff --git a/params_shard_173.bin b/params_shard_173.bin
new file mode 100644
index 0000000000000000000000000000000000000000..de19ba0d9cb4c31285ff0a05e594aa197c5d8554
--- /dev/null
+++ b/params_shard_173.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43983af7001ea4ead90a9f8c1efd79272fc35d540a58ca7f755488f8c3679a2f
+size 30269440
diff --git a/params_shard_174.bin b/params_shard_174.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f41c7028c6e439bacc6844a6960903a48e47d688
--- /dev/null
+++ b/params_shard_174.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fe51caee542b16751e5187a78d74dca36081d64c3fb68db4b7cf55d73c7c4c
+size 93978624
diff --git a/params_shard_175.bin b/params_shard_175.bin
new file mode 100644
index 0000000000000000000000000000000000000000..89ebe3ddce200ff75da6505e558a13c25a41fb62
--- /dev/null
+++ b/params_shard_175.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89ef464c5dc7a4d315c5013f540cfa5d788645c7d67682b9db45b68afbec471
+size 188088320
diff --git a/params_shard_176.bin b/params_shard_176.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5386cc2d22d9607e18d4ea6c9203a3898f52ce04
--- /dev/null
+++ b/params_shard_176.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a4049cd20132104c5f69f75f6d53eccf37abb5a5a3b73c148f053b7071c408
+size 23511040
diff --git a/params_shard_177.bin b/params_shard_177.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0969532d11f4b2b076a86884213359bb222b6f6a
--- /dev/null
+++ b/params_shard_177.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d927d116b3d871b10f97adf4c6eefba091c586571a37405ed10ec6daef8cb171
+size 33587200
diff --git a/params_shard_178.bin b/params_shard_178.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6f44d164ff2b3f534ddf0ce5c8eb76db18492640
--- /dev/null
+++ b/params_shard_178.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b648873255eaa1ff07a28f858555801e55f26864fe4768888892c0f6fd625ccc
+size 26869760
diff --git a/params_shard_179.bin b/params_shard_179.bin
new file mode 100644
index 0000000000000000000000000000000000000000..641f475c55d615f81887795f246af940e1ec097f
--- /dev/null
+++ b/params_shard_179.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:182d440797c517ac5a219086ac38bf758e29e121e76ac34da16bd8ea3c1bba49
+size 93978624
diff --git a/params_shard_18.bin b/params_shard_18.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d4331f31edbf72d85cb34212a7b3b4b6792e3b97
--- /dev/null
+++ b/params_shard_18.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc751ac82b5d925014a2aac36e8289674a10816e6a4b082cf568db5c4f8bda6
+size 33587200
diff --git a/params_shard_180.bin b/params_shard_180.bin
new file mode 100644
index 0000000000000000000000000000000000000000..111a0cddc5ff687452ad270537fb1c819702d774
--- /dev/null
+++ b/params_shard_180.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76c8022564180a8fd782a05706ef93a84ead22e5a1a065e16ffe5b66ef853c2
+size 31117312
diff --git a/params_shard_181.bin b/params_shard_181.bin
new file mode 100644
index 0000000000000000000000000000000000000000..830d69fcca20ba27bd7ca3fcfd961f84f5f9fdb7
--- /dev/null
+++ b/params_shard_181.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf0f13ba7d5180fd7c353240fba82e67614b7d7b841a267d991bb23e9c87eed
+size 188088320
diff --git a/params_shard_182.bin b/params_shard_182.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9c1a98ba6288befa8c3e5e25310878e5ea8d6f47
--- /dev/null
+++ b/params_shard_182.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b269fbdff596e47e58ddb3890d5e69d2b4c2d1e349510967fc9c819c8879c44f
+size 23511040
diff --git a/params_shard_183.bin b/params_shard_183.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e0bca07f458a2fc849875005cd80904f3caf6bb
--- /dev/null
+++ b/params_shard_183.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb033b599c253bef7be73ed804e81acce29ef0ebb9f875702eb3accbf96b23d
+size 33587200
diff --git a/params_shard_184.bin b/params_shard_184.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d7e82f77bd1a9682c9f58e89d44645f3b5e6280e
--- /dev/null
+++ b/params_shard_184.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9874686f73ff2f17074f912a5ac8e325b934ee85e30a4dcacbc5c1d98414c3f
+size 26869760
diff --git a/params_shard_185.bin b/params_shard_185.bin
new file mode 100644
index 0000000000000000000000000000000000000000..93e37a770ae3ab5753a295489c598d1175b3b73e
--- /dev/null
+++ b/params_shard_185.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2f03f66c04902b2d5ddee2ea5d993c19eefa1860687e26475ee6443eab0c58
+size 33587200
diff --git a/params_shard_186.bin b/params_shard_186.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d17be869da4cfcf9606014a2077d1ae6eed0e989
--- /dev/null
+++ b/params_shard_186.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558c5c60995da8c5e2429e2f290ed45186b7e0f28573a44d73c1de1d75d68792
+size 26869760
diff --git a/params_shard_187.bin b/params_shard_187.bin
new file mode 100644
index 0000000000000000000000000000000000000000..813e4fa0bc4fa19c1af12d1c35275a651d2a0062
--- /dev/null
+++ b/params_shard_187.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:397e03c68992bd97122bc05edc2b8a79ca4372ea5973e3177c9147b940a1f386
+size 93978624
diff --git a/params_shard_188.bin b/params_shard_188.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e04742339d77f4c7b68e5ff0376e2cf72cfc15c
--- /dev/null
+++ b/params_shard_188.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca449ef5d8efb6840adfb44a144d8aa5fd3e9b6ee161ebe2715f5ae6318feb2
+size 26894336
diff --git a/params_shard_189.bin b/params_shard_189.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2551c0be1ffa6e1f330fb669a872a920b94e6656
--- /dev/null
+++ b/params_shard_189.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787a9f733edd917fe4ef774a6acb839741981f47977074345ebae72e34a1ad93
+size 188088320
diff --git a/params_shard_19.bin b/params_shard_19.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eeb10818383da239c6c08a19216730320752b803
--- /dev/null
+++ b/params_shard_19.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9e8a58bfba3d700f318ddad01b13749daf515812202ce4b7bcc59a21160771
+size 26869760
diff --git a/params_shard_190.bin b/params_shard_190.bin
new file mode 100644
index 0000000000000000000000000000000000000000..27e1f82bcb0f85ec0b9af4206807fe3fcc6fbb50
--- /dev/null
+++ b/params_shard_190.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26278427a47234b8b332614f83012eeeef574f7bf4e256732e18982b0ab8ad71
+size 23511040
diff --git a/params_shard_191.bin b/params_shard_191.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6d278cbcf17f49956042080a204ebe2ff6bf8135
--- /dev/null
+++ b/params_shard_191.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17ccb2979adb7cd51b1c6c70f85b11323eba3bdfcf26f802ab3d39339307774
+size 93978624
diff --git a/params_shard_192.bin b/params_shard_192.bin
new file mode 100644
index 0000000000000000000000000000000000000000..60514577f2efcb22be075511a830f712059665da
--- /dev/null
+++ b/params_shard_192.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9862e2d17ba892e0b98a9a960c50c9b4c8d008433a040b3e7ed1eff34797b792
+size 188088320
diff --git a/params_shard_193.bin b/params_shard_193.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0baad16ab47a15d4586f02709699e38430d551a8
--- /dev/null
+++ b/params_shard_193.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30204076b5714139987b43e81b8f435ffe410d3f8efa548d23ff3b2ecd040a33
+size 23511040
diff --git a/params_shard_194.bin b/params_shard_194.bin
new file mode 100644
index 0000000000000000000000000000000000000000..301570e0502a7e3ddd20ae9c7607b512fdf719d2
--- /dev/null
+++ b/params_shard_194.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4f4ff0691ef6559252cb700a2d7b78c6479459eb1c35ba61c1622f5755c4d1
+size 33587200
diff --git a/params_shard_195.bin b/params_shard_195.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6651f49904232f548f4beb5ad32b3f31379e50ae
--- /dev/null
+++ b/params_shard_195.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08c659f1b595463bb7da0da35b6cd9ba1d55b18cf9c6aed1582feeb2f05a46f
+size 26869760
diff --git a/params_shard_196.bin b/params_shard_196.bin
new file mode 100644
index 0000000000000000000000000000000000000000..05b6b51395554a24f75e2115f8c436dcc485e871
--- /dev/null
+++ b/params_shard_196.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b8da213b8b523cb644cd2dc80f7b5973be5c1010ea9736c3a1f619b34f862f
+size 93978624
diff --git a/params_shard_197.bin b/params_shard_197.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c699f71affbeba73ad1f69ce8adc25a37b2a8eb7
--- /dev/null
+++ b/params_shard_197.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faca1f307eadc2afde1690798a4222a51460eafd289776877f9d986aa86a09b
+size 31100928
diff --git a/params_shard_198.bin b/params_shard_198.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8f6250ba69918782c0670a2b395cd4b11a1e9c74
--- /dev/null
+++ b/params_shard_198.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bf3b66ef79eb42da4f162c7fcd359ae7ec6e4aa61c20ae1d46e1342aae9132
+size 188088320
diff --git a/params_shard_199.bin b/params_shard_199.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ffaae8ecd13749bdeb7ff14c34c81d6a9ca1f57
--- /dev/null
+++ b/params_shard_199.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def484e36dc85417a1ed3685922aa91db6cf516662a5e5793822f45cc9eeb078
+size 23511040
diff --git a/params_shard_2.bin b/params_shard_2.bin
new file mode 100644
index 0000000000000000000000000000000000000000..913f328f0ace633c34e9772f5f9e1db49a4d919c
--- /dev/null
+++ b/params_shard_2.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6be4ab125bf4b5dca075e9c9b32a31b1a942bd9a8cab2377e6e56fecdda1c6
+size 188088320
diff --git a/params_shard_20.bin b/params_shard_20.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ea5c0c187635f203545a3006e62abcb3e0173818
--- /dev/null
+++ b/params_shard_20.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5918fb2b9b9ef6faa23f82a2eaf9ef69c563299e291e694d614b5bbb26f6ed65
+size 31068160
diff --git a/params_shard_200.bin b/params_shard_200.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0bd387d9d1c1ba942659c4f385ed9d7165ef648f
--- /dev/null
+++ b/params_shard_200.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09dadd36c8521beb69a757d5bb97788b72312b6f752a4577b5e532400274b4d5
+size 33587200
diff --git a/params_shard_201.bin b/params_shard_201.bin
new file mode 100644
index 0000000000000000000000000000000000000000..68f017333e819cef943ec865eba1a79f45054b95
--- /dev/null
+++ b/params_shard_201.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975b57fdcf394161e1bc7fa34a2b1b2034a24f7d8ec53384ded4626d760d4c6e
+size 26869760
diff --git a/params_shard_202.bin b/params_shard_202.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5850f6dabb8258540f45e8cf7378f51a4386410
--- /dev/null
+++ b/params_shard_202.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25afa4fe8771908ecda99e32979b5fa860cf6568e651ac1633579ac5c4e7284
+size 93978624
diff --git a/params_shard_203.bin b/params_shard_203.bin
new file mode 100644
index 0000000000000000000000000000000000000000..af35920c5d942e0e4bff9946a2d01f8d46c4cf98
--- /dev/null
+++ b/params_shard_203.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a9b379a6d190ec6ddbead81140e7d7396338596a382f5ed66258df3d079ceb
+size 188088320
diff --git a/params_shard_204.bin b/params_shard_204.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fb87c4a3eb987939d9fa7206a1ff2fce21e52393
--- /dev/null
+++ b/params_shard_204.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee91cfe6a6aae35392a0420c580934f3798b2decc97192af233b1ec2571f73e5
+size 23511040
diff --git a/params_shard_205.bin b/params_shard_205.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0dce851d80bfd871dee8777686ed42619b3fe1e0
--- /dev/null
+++ b/params_shard_205.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64fe6bfe322f5399a7c495ed8333a84bde57307a69b858effe2328e5369f879e
+size 33587200
diff --git a/params_shard_206.bin b/params_shard_206.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7f2d9428abe86b353a204eddbd32e968aa1f530c
--- /dev/null
+++ b/params_shard_206.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3aaeedf73a28b38b6d413331589f9f86acb815a5fb9dbb061d1b33206e88d9
+size 31117312
diff --git a/params_shard_207.bin b/params_shard_207.bin
new file mode 100644
index 0000000000000000000000000000000000000000..51495754a1ce62c94f89ad903855d86f9c8e470a
--- /dev/null
+++ b/params_shard_207.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb54e64a61b9d4e5ccf088c061c9e046739b8b43d7705452588076507d5e3b8
+size 31068160
diff --git a/params_shard_208.bin b/params_shard_208.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cdbff7685c606270ab3afe19e947ba0e4f7b37e2
--- /dev/null
+++ b/params_shard_208.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c2747a26099e075177379d02e8ef6e8101e6ff8e9c32f73fab3455a517d369
+size 93978624
diff --git a/params_shard_209.bin b/params_shard_209.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fdc8daa65af548a6b0c6e13eb7357eeb0213ac99
--- /dev/null
+++ b/params_shard_209.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e580485af4278c72f72ea4ffe34fdb2aeccc7b5ba01099711f605b4411e893be
+size 188088320
diff --git a/params_shard_21.bin b/params_shard_21.bin
new file mode 100644
index 0000000000000000000000000000000000000000..82a7796ed0df0a33d86491d0ac5ff6bb33151fe2
--- /dev/null
+++ b/params_shard_21.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b7ace6a605f4939d95e913cd293a48bd23141b29d0574d318a916f81f29785
+size 93978624
diff --git a/params_shard_210.bin b/params_shard_210.bin
new file mode 100644
index 0000000000000000000000000000000000000000..96ec4b33de4745f027ee5b627c22c602c36c28b2
--- /dev/null
+++ b/params_shard_210.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69166cfeefd649871266b3a41813767d7fbe8289c24640be3b3ae5662975b9be
+size 23511040
diff --git a/params_shard_211.bin b/params_shard_211.bin
new file mode 100644
index 0000000000000000000000000000000000000000..46b64d285cf46a869d4d188dd0cf588d42ca9aef
--- /dev/null
+++ b/params_shard_211.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007ef92e029d43a7bbdaefda8263522a821c6531c37719aed9b3444a7a204940
+size 33587200
diff --git a/params_shard_212.bin b/params_shard_212.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b39d21fdbc3d68e8dee0450743c74af90bb8da1b
--- /dev/null
+++ b/params_shard_212.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c362af0dc434e9891b0787f942c289f4887b1123605eccdb0452df8c114e09
+size 26869760
diff --git a/params_shard_213.bin b/params_shard_213.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9d223a12b539b526064c5633462f7b876155465e
--- /dev/null
+++ b/params_shard_213.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87f6f15084452cce0fad0de463669766dea03f10531666b1301331aedf703cf
+size 188088320
diff --git a/params_shard_214.bin b/params_shard_214.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fac523474b933f83104faeb4c2861a4414f4c274
--- /dev/null
+++ b/params_shard_214.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccec4c74f54eea1320587451a31dfdf887319f76917ce8cb1fd9e95dbc9ce86
+size 23511040
diff --git a/params_shard_215.bin b/params_shard_215.bin
new file mode 100644
index 0000000000000000000000000000000000000000..558ee9275d44e4198000107548e4c77fb499af08
--- /dev/null
+++ b/params_shard_215.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22788449e4d57a1dc8bc7ffadbed70f95684b359289ed20e6fd218ffc223293
+size 33587200
diff --git a/params_shard_216.bin b/params_shard_216.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e96977b404b1edb29f41b75fea106c89a8ba3e55
--- /dev/null
+++ b/params_shard_216.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddac37e901fdcb323a5ce203fe5115a9147adbe7511da35331f127ffcd5e309d
+size 26869760
diff --git a/params_shard_217.bin b/params_shard_217.bin
new file mode 100644
index 0000000000000000000000000000000000000000..403cf666817c9c001a3e23e242509a8c685a8ea1
--- /dev/null
+++ b/params_shard_217.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c86c11fe666147dfabcaaa8c203512a1d92db606bf12439ae7ee1270c9165d0
+size 93978624
diff --git a/params_shard_218.bin b/params_shard_218.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ebdfb7556719a0daf06bbc9d2b6030c316507539
--- /dev/null
+++ b/params_shard_218.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886c817ce4f70dc53a203265922b0aa03eaa7b266b368d0bd0a4471acc853083
+size 30269440
diff --git a/params_shard_219.bin b/params_shard_219.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9df67d42de68b80146ea2d6948a2734cf70f065
--- /dev/null
+++ b/params_shard_219.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25155062fa8b3961ef6499a7ac7b02f2c7629cc4061278038193e40492fd849d
+size 188088320
diff --git a/params_shard_22.bin b/params_shard_22.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4185229b26af80e2a84ad3cac50a321ba5ad48d0
--- /dev/null
+++ b/params_shard_22.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6356d4b6c2b88e8657d3a0ea70b7360e0e6b5a972d47f69a001bc4bb1ebc2cb0
+size 93978624
diff --git a/params_shard_220.bin b/params_shard_220.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ddd76ac0ecd1d4dd7c8fc4c26753d66884d4c73
--- /dev/null
+++ b/params_shard_220.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251dc5db68c9bca90ef9d999c934132e4f65efaf48984468072db12a2a588ea7
+size 23511040
diff --git a/params_shard_221.bin b/params_shard_221.bin
new file mode 100644
index 0000000000000000000000000000000000000000..caf282eba869e6ce23a3e186eedcf98ada87878e
--- /dev/null
+++ b/params_shard_221.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9300efc66cb5768468776aaaf1e2d33f193520025fd51e334bbd075bd0718c27
+size 93978624
diff --git a/params_shard_222.bin b/params_shard_222.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f4925322b22143023d2ee0b7358c2f252a97325
--- /dev/null
+++ b/params_shard_222.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2c6f73cbc320eccf63487329145f28828dbcba81adbcf9615811ba0d9e4884
+size 188088320
diff --git a/params_shard_223.bin b/params_shard_223.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1ed4a1adf7bd493d2a9782bfda81c049669b94d4
--- /dev/null
+++ b/params_shard_223.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c707efbfbeaafe667b1390d1aaba868883111ac9d4c29570a9e2dde31ac381
+size 23511040
diff --git a/params_shard_224.bin b/params_shard_224.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a2d0a0ee2368cee0dd0c3f7dd0ec200886419047
--- /dev/null
+++ b/params_shard_224.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62870dedafdc457535dfd5af6adb7af5e7b3e8fe597a425965d928b04b6b9cae
+size 33587200
diff --git a/params_shard_225.bin b/params_shard_225.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b056fc1ec362db83f49c28360a66c349e8c830eb
--- /dev/null
+++ b/params_shard_225.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc602c735d447a5f0d3a0b40c8a3ed343fb5045c09d7fa060032129353a13c8
+size 26869760
diff --git a/params_shard_226.bin b/params_shard_226.bin
new file mode 100644
index 0000000000000000000000000000000000000000..175bc911adac8a0b731772421b12f66d9d2acb6b
--- /dev/null
+++ b/params_shard_226.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0461f97dc23d926644b581740ff70b686d2e81b679a1bf2fcb0227dcab39f313
+size 93978624
diff --git a/params_shard_227.bin b/params_shard_227.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ec93f804c7f73396d8a247596d8f9ebb0cb023f4
--- /dev/null
+++ b/params_shard_227.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f853796bf2906b6fd4b9b59940592a40e7a87c351b53b08e396f103e5a4c978c
+size 31100928
diff --git a/params_shard_228.bin b/params_shard_228.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b5f4c2f065075b4425cc42a72cc2f9896583ff8
--- /dev/null
+++ b/params_shard_228.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f1a7eef8751f559b8cbb4bbd3a6f1913bbe2ecf9b635459d89ff27de323853
+size 188088320
diff --git a/params_shard_229.bin b/params_shard_229.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3ae72c749e7c381ba36bebda3ab84db30ae69e7f
--- /dev/null
+++ b/params_shard_229.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261046549e855adf61bcb2ae34154e2f6542da553dc2d5145c2fec624ece02e2
+size 23511040
diff --git a/params_shard_23.bin b/params_shard_23.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e2db469fe2f3b5f2a2434dc1e5545e4bd2bbc4ef
--- /dev/null
+++ b/params_shard_23.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584b3780e6ed51e94c1d4b695bf41eead50dddb29c655c7f01e56a3fa6d84254
+size 188088320
diff --git a/params_shard_230.bin b/params_shard_230.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4d99fde8681357424a2e6a64cd89176c7e1ab2e1
--- /dev/null
+++ b/params_shard_230.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca20d309849020578eb9c4e0f8ae1e1ffe392a8b683b1505acc1d8a8b0add007
+size 33587200
diff --git a/params_shard_231.bin b/params_shard_231.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d862285a95a4f39ee995479d18e05d11a9d3afcd
--- /dev/null
+++ b/params_shard_231.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc5c824d3c9408f72e7bc27bbd2b84dc56f1f0ce97c4d1679352fca26d38163
+size 26869760
diff --git a/params_shard_232.bin b/params_shard_232.bin
new file mode 100644
index 0000000000000000000000000000000000000000..94a236dad8258cb8420676d8590f2fd5e851b97b
--- /dev/null
+++ b/params_shard_232.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e2cc65bb6ef60e7341135877ad294d7bc8fea459a3fd6902919fb849f02c32
+size 93978624
diff --git a/params_shard_233.bin b/params_shard_233.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c37862fc6974ea6ab4ff8d0aee06554c0b1b8f19
--- /dev/null
+++ b/params_shard_233.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2e6f4b74a7a817ea3244345e2798a533a4492832914905027c9609dc90b04d
+size 93978624
diff --git a/params_shard_234.bin b/params_shard_234.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e0c475d4f3201eb699f666b0594f328f2ac4834
--- /dev/null
+++ b/params_shard_234.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e58bba00bed85cc50b0fdd99a4fd06f96acd15b2b231cee6e70d2a84f188cc
+size 31100928
diff --git a/params_shard_235.bin b/params_shard_235.bin
new file mode 100644
index 0000000000000000000000000000000000000000..beb466dbb06741e2bd2ebdd65f9329c285e4481e
--- /dev/null
+++ b/params_shard_235.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695a65900be49ea8f20eba6cb33f57d9f4036294448f695d2d67c9056a954165
+size 188088320
diff --git a/params_shard_236.bin b/params_shard_236.bin
new file mode 100644
index 0000000000000000000000000000000000000000..23e68ffa74720c8ecceb9c8e65918986950d5362
--- /dev/null
+++ b/params_shard_236.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b4a84692b22a58c47a02d02e4b4135603033e8493f7fd0ebbb93effa82b3ea
+size 23511040
diff --git a/params_shard_237.bin b/params_shard_237.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9a2a753d377329a7ce901c69895ddf709435fad7
--- /dev/null
+++ b/params_shard_237.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5da5a319cf34bf491142d323561efb0e37906ea2b45be98244987cd439e35f9
+size 33587200
diff --git a/params_shard_238.bin b/params_shard_238.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8f4df0a59eafe1784f1771c3ed2939a965a3850a
--- /dev/null
+++ b/params_shard_238.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233dabf5223a7baa2fed6ce08e89265350ee9703c9df308b15e52d6a75974884
+size 26869760
diff --git a/params_shard_239.bin b/params_shard_239.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dbc9943d853227e94050cd9619ebcda39d66f37a
--- /dev/null
+++ b/params_shard_239.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93eb689c9d1da00c2f57ff226976865fe479fc6fa4d014884d5cc5ff431ad00
+size 93978624
diff --git a/params_shard_24.bin b/params_shard_24.bin
new file mode 100644
index 0000000000000000000000000000000000000000..98ce12048983a002f8b0c27de25d810d449e0234
--- /dev/null
+++ b/params_shard_24.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8685c9940d151aad9e24bc62b09bd953a1ea6e9644eed5559c104a8db102e61b
+size 23511040
diff --git a/params_shard_240.bin b/params_shard_240.bin
new file mode 100644
index 0000000000000000000000000000000000000000..57098cd116e116e9fbf5c6e35ca3aea48975dd91
--- /dev/null
+++ b/params_shard_240.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3830bf4c9a63a2dbf87d5d8e35e08958db251971611d4d65088962ff2a57eca
+size 188088320
diff --git a/params_shard_241.bin b/params_shard_241.bin
new file mode 100644
index 0000000000000000000000000000000000000000..74a742e0eb06ce8295a5f42203abf475baf4102e
--- /dev/null
+++ b/params_shard_241.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6d30c30be6772a553ce4a67a7ac2304f588d7c79a316668428f9eb3e1ced49
+size 23511040
diff --git a/params_shard_242.bin b/params_shard_242.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1c35f86d9b3aa6baec3041cf6605986099d64eb6
--- /dev/null
+++ b/params_shard_242.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd097bc57014325935b8e25e36b3b62858f7ece9407f7309d2153d40b9aa192
+size 33587200
diff --git a/params_shard_243.bin b/params_shard_243.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a02c773288629193470127cc9803c0fc65c73d43
--- /dev/null
+++ b/params_shard_243.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2606933513b8b2267040058417da475cbe6c4c08fa463e62ccbf564a456b88b
+size 31100928
diff --git a/params_shard_244.bin b/params_shard_244.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c9c668ab2e167fbe860bd267a857c687ea4efcd
--- /dev/null
+++ b/params_shard_244.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2db87e2b95358dfc38169c99fe4a86a09ea85a8347c51d3659ecc0cd437a53
+size 31068160
diff --git a/params_shard_245.bin b/params_shard_245.bin
new file mode 100644
index 0000000000000000000000000000000000000000..872bb1b06f0b79e2b249956c65f42a08d1228d8a
--- /dev/null
+++ b/params_shard_245.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62fab3a6a92c622edeee93c3011bb4b39b9611e95d25e49caf4962db617a82f
+size 33587200
diff --git a/params_shard_246.bin b/params_shard_246.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e50f4be61270ef6c840da4451952b5c996d9adad
--- /dev/null
+++ b/params_shard_246.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7aff4e02f9d7b1d0ebb8924672e758828d4b84e05b819cf61d468d02d307d2
+size 26869760
diff --git a/params_shard_247.bin b/params_shard_247.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bfbd29477b86ff08a14d0b503a840dc052c76e4f
--- /dev/null
+++ b/params_shard_247.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf80a6b5424ac85bee1633e98192f54ab14c7b0c83ae3e670d835380ac4844b
+size 93978624
diff --git a/params_shard_248.bin b/params_shard_248.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d8b4d34782f253d24e2dabecf5523c831a96421
--- /dev/null
+++ b/params_shard_248.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d317015dd166bf21d59a426c22d97fa0aab072d2c7f30a5882b3f541ec0d55
+size 188088320
diff --git a/params_shard_249.bin b/params_shard_249.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cad2a30ba2f79461b6a1418aae2fd00c5457e271
--- /dev/null
+++ b/params_shard_249.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225658cb64866f3aec534be51544b06f27a61c18bc8ffa80e9ce623eb82b1687
+size 23511040
diff --git a/params_shard_25.bin b/params_shard_25.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ea41aadbc01297d2b59306dc21d90b492dd70020
--- /dev/null
+++ b/params_shard_25.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a4ae6606616061fa200f0d796fd839b81c738b9c53503f8ecc825d918a2a15
+size 33587200
diff --git a/params_shard_250.bin b/params_shard_250.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f1ea9b1b42cd2c364d618cd8bff0f2ffa314af3
--- /dev/null
+++ b/params_shard_250.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd3e47d5e179387058b88d01360a2e244b185552f63b6d87719a23c8e6590a6
+size 93978624
diff --git a/params_shard_251.bin b/params_shard_251.bin
new file mode 100644
index 0000000000000000000000000000000000000000..34efe467dc55db37231bc1ab0d74cd708e7b8a1a
--- /dev/null
+++ b/params_shard_251.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7e25ceef0bb2c260f2dc4e365ec4ac0c0d97e7d833679b4ffb00c67bce8d8d
+size 22712320
diff --git a/params_shard_252.bin b/params_shard_252.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ca30ffeb3b20a92a163d45dcd64ae1adbd654344
--- /dev/null
+++ b/params_shard_252.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cef5d746eaa3ee6fccb02ca30ab50bc4dcd75c1f4ea9279f0d2d1fb409a0d28
+size 188088320
diff --git a/params_shard_253.bin b/params_shard_253.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1279d6a73c2ea9ee562da1e0bc7107938b8b2d1d
--- /dev/null
+++ b/params_shard_253.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6e60173cea78f7fdc285e2e8e56d76ad69c7675e0dac62f03d7a0701c1769d
+size 23511040
diff --git a/params_shard_254.bin b/params_shard_254.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7c16f896dd11507f32cf6eeaf396d7e5620abc14
--- /dev/null
+++ b/params_shard_254.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f4c20b96d11e262b040de4c675ff0eee15fb5290d8874cbbca519d75ec9729
+size 33587200
diff --git a/params_shard_255.bin b/params_shard_255.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6b10fb11fe516e45925d311f0a71cd3f702f3bda
--- /dev/null
+++ b/params_shard_255.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913afe787c95f01f8bf61cdf0eb1d40a87960acb3ad0687fc617be75308fbdd6
+size 26869760
diff --git a/params_shard_256.bin b/params_shard_256.bin
new file mode 100644
index 0000000000000000000000000000000000000000..90888e845e64e9c8471f8cf6cc6ecf57a5cf2de1
--- /dev/null
+++ b/params_shard_256.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0138f909f594a6fccf38e0f2a2a18356cddcb440f1e121fe20513823034f37a0
+size 93978624
diff --git a/params_shard_257.bin b/params_shard_257.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f8aed43b0258ea8ea300cea525d49f64b69ab372
--- /dev/null
+++ b/params_shard_257.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0855261e57617bb22981ca6c59e72d5a7d02b89835b1e85eb0379205e8c0c4c5
+size 188088320
diff --git a/params_shard_258.bin b/params_shard_258.bin
new file mode 100644
index 0000000000000000000000000000000000000000..beb3b8930bc88800a76db23757fb76d068c0fd14
--- /dev/null
+++ b/params_shard_258.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004c1f33a372ebb1e7c3d465d631fea3cffe3ae53b6b1ca4a294e79052fef996
+size 23511040
diff --git a/params_shard_259.bin b/params_shard_259.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9deff05168ca70e1eeefed97d63c330bfe6f014c
--- /dev/null
+++ b/params_shard_259.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51372caf729dad00397ad0372e9ecba6c6e8d5233e14dbafb4db5d3d39f4e1c9
+size 33587200
diff --git a/params_shard_26.bin b/params_shard_26.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e25180c03081d7f2001eae4d0192a3c90129e40
--- /dev/null
+++ b/params_shard_26.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5fc153fb2a524602f3de100ac83bd875b850cc44ef44465e54dc40f7dc59a04
+size 26869760
diff --git a/params_shard_260.bin b/params_shard_260.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9fa6aa29a5c9b70881f0185b5ea9617d61f796f2
--- /dev/null
+++ b/params_shard_260.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d845ebb5862b6462efcf8cc706b19c3175ca3c7348889b8fb6822cb433965be3
+size 31068160
diff --git a/params_shard_261.bin b/params_shard_261.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2f6a9e65dc9cc328f73081371765ce9e96e92734
--- /dev/null
+++ b/params_shard_261.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c5f251af45c13a8a1e95a69931d805316faa3e8f21ff36f99a295209d76cf5
+size 31068160
diff --git a/params_shard_262.bin b/params_shard_262.bin
new file mode 100644
index 0000000000000000000000000000000000000000..710f0f5a3b2258e8dc84df02eb0b438f625cae1e
--- /dev/null
+++ b/params_shard_262.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36245bde8975d9a9330f32260be340c2fcec4745be7f5284edcb88b256f0d16e
+size 93978624
diff --git a/params_shard_263.bin b/params_shard_263.bin
new file mode 100644
index 0000000000000000000000000000000000000000..260702de28380eef0d16c9981cfe70c481b2af32
--- /dev/null
+++ b/params_shard_263.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753f426d0bba767b72205bad0105db59ee812f196194e748d600b18d1934d37a
+size 188088320
diff --git a/params_shard_264.bin b/params_shard_264.bin
new file mode 100644
index 0000000000000000000000000000000000000000..67a027330044563bc6f9ceb3b0becb13d5a132fd
--- /dev/null
+++ b/params_shard_264.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f392b8e4d942f007029b3a91080796c4dc26ff6d04b5bec88b57b9f22cc580
+size 23511040
diff --git a/params_shard_265.bin b/params_shard_265.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e98c23d59cca7a054480c5090f37f1eb58584610
--- /dev/null
+++ b/params_shard_265.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb7236bfb276dd71ff32569a4d8c89d6d0534892822c9ce7d6a1c3b3189f36f
+size 33587200
diff --git a/params_shard_266.bin b/params_shard_266.bin
new file mode 100644
index 0000000000000000000000000000000000000000..097ba9359d8312d2896780e43fe52723fad80f9d
--- /dev/null
+++ b/params_shard_266.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd685b67c8e93cc5e10516bafb86255089fee8f1b93f62d3f82f9764ce9754b0
+size 26869760
diff --git a/params_shard_267.bin b/params_shard_267.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5cb0af13a13956dc6c38254761487c8e1660dfa7
--- /dev/null
+++ b/params_shard_267.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ecfb9036db025512988bbde2c171fd273bc96e7532d50675d0c271477cbd21
+size 93978624
diff --git a/params_shard_268.bin b/params_shard_268.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ee45941f2e2223ef498a7d24200b5081b7816c3
--- /dev/null
+++ b/params_shard_268.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f4de7e57814921f5ca49680bc6e00f938fedb82b9856fdf64becdf183ffaad
+size 22745088
diff --git a/params_shard_269.bin b/params_shard_269.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a4bac1d42ea8d389566b745ed48e313fe6026c4
--- /dev/null
+++ b/params_shard_269.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c20eaa9a065a479144760f30c0606d4784d0f4e0704cfb81ee94b533ce1e2f
+size 188088320
diff --git a/params_shard_27.bin b/params_shard_27.bin
new file mode 100644
index 0000000000000000000000000000000000000000..342007bf5e90f1d2a4900729fffc11d7482908e8
--- /dev/null
+++ b/params_shard_27.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac9f9518551b2d6a2be22d992107afe902e4819d7cd5f2a62d3688520e2d19e
+size 31117312
diff --git a/params_shard_270.bin b/params_shard_270.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3fb0e4409073c0697721d9c9e46ab2f69bd84642
--- /dev/null
+++ b/params_shard_270.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e22c2a7844063d27ab959c595d55c707dd53a2bfcb28e6624d9adfe893837b
+size 23511040
diff --git a/params_shard_271.bin b/params_shard_271.bin
new file mode 100644
index 0000000000000000000000000000000000000000..111397242d7517db397ed1906ff4b487d9fa45bb
--- /dev/null
+++ b/params_shard_271.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba71a7ab4cec81ee245d8dd0c458238def087a159157a160060d17202a4a763
+size 33587200
diff --git a/params_shard_272.bin b/params_shard_272.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5f1baf49dd1efbbb9735104312f11d2b9045b07
--- /dev/null
+++ b/params_shard_272.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35ece655953d090dad32ad54e40ef6392ff07dc42764b855f5b006da0744e6b
+size 26869760
diff --git a/params_shard_273.bin b/params_shard_273.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2feb32161051a305f81f287250e5ad6a18fe19a1
--- /dev/null
+++ b/params_shard_273.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01efde100396e19bf59e55c9d4f4f17ae0b1c89c5ea3b6205808b518741e7d9
+size 188088320
diff --git a/params_shard_274.bin b/params_shard_274.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cc37844673e57a59ea75241fd7b5bb6361fc8d9a
--- /dev/null
+++ b/params_shard_274.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6973e2242342c8b7e733fd0d95ea1e9f2b1bdadfef6c7ea1b95a28c978848d76
+size 23511040
diff --git a/params_shard_275.bin b/params_shard_275.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d6d23508ad7050dc13c94ce83428180856afb167
--- /dev/null
+++ b/params_shard_275.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d6a11f6ea6f584bdc2edcc53380904a6e6d5dd9114ad97f10490be7e9cb4f4
+size 33587200
diff --git a/params_shard_276.bin b/params_shard_276.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c86b4b0ac8dafba1ce978827eeb97f2ba641db21
--- /dev/null
+++ b/params_shard_276.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355ac2e0a5fff46284935b5e4040969b524971a6db20eaf7fe84622b53909e53
+size 26869760
diff --git a/params_shard_277.bin b/params_shard_277.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c583c897635665879df3cebc9eb10b709d83a2f2
--- /dev/null
+++ b/params_shard_277.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6dd644ab8e7b9b93d983630a81419d8b8b3735d0cd8d0848fbda013764d358
+size 93978624
diff --git a/params_shard_278.bin b/params_shard_278.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7f08ed6caa059ab6cff314a3f67dbeb4dd31ad61
--- /dev/null
+++ b/params_shard_278.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f87c83c9dd8e08263fe8767df892812cf50d4935b175061d75844c12bbf0a05
+size 26894336
diff --git a/params_shard_279.bin b/params_shard_279.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d1a6fb8b3fbf8628c0ae6a8b2afc47873fd0cd06
--- /dev/null
+++ b/params_shard_279.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e28c97ce3d0295527eaf814c1296ac7c6fa3e14d2108feed3cfdee5c14a31f
+size 93978624
diff --git a/params_shard_28.bin b/params_shard_28.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ed5fad640313d640c33c63c6fa1ce12e3177ccc
--- /dev/null
+++ b/params_shard_28.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97ca582d421744c6823b3938cf031db20c65eaddc8acc6caee03f8d97f2e9c4
+size 93978624
diff --git a/params_shard_280.bin b/params_shard_280.bin
new file mode 100644
index 0000000000000000000000000000000000000000..097f126f5e891945da5456aabf9336da9b3fcc0a
--- /dev/null
+++ b/params_shard_280.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9394b03f34559634ec4cc9c527c3d752363945bf6976f3d054a6d1de974ee3ca
+size 188088320
diff --git a/params_shard_281.bin b/params_shard_281.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5dfa55b036ec71d585029edade52a27df8e051dc
--- /dev/null
+++ b/params_shard_281.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42aab3be6462fe523d8b4f103e8bf96f5ab43cf8529d693103408f90f14019fc
+size 23511040
diff --git a/params_shard_282.bin b/params_shard_282.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4855d6088670119d1bb2110ca2605ea5b4f93b00
--- /dev/null
+++ b/params_shard_282.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0950ae593abc7064f882f18c084bb29aab9f5fdfd15b6c140fc23d45e28d14b6
+size 33587200
diff --git a/params_shard_283.bin b/params_shard_283.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5f086d9e8013de48baf59a8a3016314eb1a43308
--- /dev/null
+++ b/params_shard_283.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2e316c02fd47851a7038666fb6c34b7208889251ba6772a4bbfbb02761ccd7
+size 26869760
diff --git a/params_shard_284.bin b/params_shard_284.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0cca0c5981b12935303dd365b166c3c8e3867042
--- /dev/null
+++ b/params_shard_284.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ca79e7132e517f91d9ccd41b5639ba53692790186af3f9a9dedcc11428465d
+size 93978624
diff --git a/params_shard_285.bin b/params_shard_285.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e744244cc9c67146aae88fb61fd36456ce93b2c8
--- /dev/null
+++ b/params_shard_285.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4b6a91cd7fcb8f25ce52fcc7520678e8ee451e9c661e5275a58c722a054e06
+size 31117312
diff --git a/params_shard_286.bin b/params_shard_286.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cbe430f21dd3b75c9f7fd8215f76b5f37a9de154
--- /dev/null
+++ b/params_shard_286.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553736f0f9203fcf0f2879ac86e5f2daf4b94ce750a8d4a2fd7ed6feba689cd9
+size 188088320
diff --git a/params_shard_287.bin b/params_shard_287.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f8076672b4633b7f03eff5ebbb1bd99fd479a577
--- /dev/null
+++ b/params_shard_287.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49246c45dcf2364d7106962b4606e354e61dfe24960bed0b25c9f9addc365ed
+size 23511040
diff --git a/params_shard_288.bin b/params_shard_288.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ffe50116da496607e27d8579c6b577e7f8b4f7ef
--- /dev/null
+++ b/params_shard_288.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bb611f43e7e6a9a1bf6becf08429847e13c70ffced2da2d29422196a37833e
+size 33587200
diff --git a/params_shard_289.bin b/params_shard_289.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3420777b24ed5a6648e62717602381b78f2498d0
--- /dev/null
+++ b/params_shard_289.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7bd05bf218374c409e2320d6b662b922c0bb4312fe270dc26e3801a728fd0e4
+size 26869760
diff --git a/params_shard_29.bin b/params_shard_29.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0ee4c358649ad32de7a57d5f4d9cdb7d21e0b4d9
--- /dev/null
+++ b/params_shard_29.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e7dceb44ff6463f8f9ca79f265cfa11eddff12a3353d2ec2ad60bbf72c2980
+size 188088320
diff --git a/params_shard_290.bin b/params_shard_290.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c3ebc45a16c6d716f7db879fd5eaa037c7a28646
--- /dev/null
+++ b/params_shard_290.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d23af06d14253df067f49dfe1c3c99ce6cc498715d793df0629b9facb9ce5c9
+size 33587200
diff --git a/params_shard_291.bin b/params_shard_291.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7ad4d4f80149bf437851717b5acd1066424dd07c
--- /dev/null
+++ b/params_shard_291.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ebdf2a334437c44b19206f267f4b4676c5610a60ba6e4f2960a42d7a2acc721
+size 26869760
diff --git a/params_shard_292.bin b/params_shard_292.bin
new file mode 100644
index 0000000000000000000000000000000000000000..780d72cc3bda1307d2c999bd855ff88be7393420
--- /dev/null
+++ b/params_shard_292.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de550ffb15f296e374187c93ba49172ca021cd9e0dfedf644ac477ce226e9b1
+size 93978624
diff --git a/params_shard_293.bin b/params_shard_293.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d89ee49604ed0b37c55ac1e1d20f5b2d7c236879
--- /dev/null
+++ b/params_shard_293.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349f7e64e98aed220f4d0bca5bb1fb2e1d8c9c067653fc3b714f4e7c6a944fcd
+size 26894336
diff --git a/params_shard_294.bin b/params_shard_294.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4d7dd9ded8b0be4fc3696f2e7f33a8991dca54b3
--- /dev/null
+++ b/params_shard_294.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e286143c0cf82e3c5c7ad9a77c2d3e9ef6603cbc1a0a1245de3010b3f8542a
+size 188088320
diff --git a/params_shard_295.bin b/params_shard_295.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2891ca8aafd82a54a1c931c8f75e3d9c7095f34a
--- /dev/null
+++ b/params_shard_295.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec47912adbfebd19d7ad72e3fe18c594a9c238b82a5ec845f7c8c443ac1c9cd
+size 23511040
diff --git a/params_shard_296.bin b/params_shard_296.bin
new file mode 100644
index 0000000000000000000000000000000000000000..57a2e5b6b5425226642875939746bc9cd98ba264
--- /dev/null
+++ b/params_shard_296.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32aa644d28906b90d00064ddeed2d818440883b2d274b5c016e3d91975d3e4b8
+size 93978624
diff --git a/params_shard_297.bin b/params_shard_297.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aedaa747230944281911ecfe30683aada25245d8
--- /dev/null
+++ b/params_shard_297.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623dd75748c39056a967225ccb528efeade53d6f1db87c5a023605601179acd9
+size 188088320
diff --git a/params_shard_298.bin b/params_shard_298.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4387fca9f909d3fc93926b85fbd12deaba50fef2
--- /dev/null
+++ b/params_shard_298.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab07aafcaf96836c3b0b6d50939c6d6002f237537eec115345e345933a5f7d4
+size 23511040
diff --git a/params_shard_299.bin b/params_shard_299.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f107dd36dab506baf87e91d29d00083eae6ce2e8
--- /dev/null
+++ b/params_shard_299.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2692a008f6124bcb180c29259fa5301a3519f6bb91775df714596e8c78181602
+size 33587200
diff --git a/params_shard_3.bin b/params_shard_3.bin
new file mode 100644
index 0000000000000000000000000000000000000000..08a003e5863d41358e3f7a11ce782eb359f34ffb
--- /dev/null
+++ b/params_shard_3.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949aeec4c66d9e126e72f037ca61abb22e6847727b83a632e7f455620d86beef
+size 93978624
diff --git a/params_shard_30.bin b/params_shard_30.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c6ce02b919a44e434793b771f9fce5ee627971d8
--- /dev/null
+++ b/params_shard_30.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77212d230654f205960b5fed1e0b64257fa54e5317e931eb9cef9015b8668748
+size 23511040
diff --git a/params_shard_300.bin b/params_shard_300.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0a01fc61ca66b9a0495fe913f367ab06e59e2617
--- /dev/null
+++ b/params_shard_300.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e636faa03bc0b2c5bf82e1b0f34137a3c314deded8a14ae97e0fd36cebd57a6
+size 26869760
diff --git a/params_shard_301.bin b/params_shard_301.bin
new file mode 100644
index 0000000000000000000000000000000000000000..628d6971dd6b5818ef5f07e4b42cf69a23fa0fe4
--- /dev/null
+++ b/params_shard_301.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0d20178afd8735c3e756e1b2c621f9fcc9fdfa2f2c22c96b061135be90b2ec
+size 93978624
diff --git a/params_shard_302.bin b/params_shard_302.bin
new file mode 100644
index 0000000000000000000000000000000000000000..46ecd0662cfa0cf8cf9fbe4e097f46862e9d9650
--- /dev/null
+++ b/params_shard_302.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227f651a9f0de6133acbbee4ce0107b684e6f52b7dd287b344e43d765a393502
+size 31100928
diff --git a/params_shard_303.bin b/params_shard_303.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e995687fdb152b19fcf9dbe29de04919fba1263
--- /dev/null
+++ b/params_shard_303.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3712450238e9076d3bda3e4cd9515a786148c6202177d97b647f7baac4b3e44b
+size 188088320
diff --git a/params_shard_304.bin b/params_shard_304.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c2b43bc499d0aa3206e45207c29ec01b427b0b2c
--- /dev/null
+++ b/params_shard_304.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ffa50aa6866926d5ff995964923843cb599adabfd6404c782569ce3d4436a9
+size 23511040
diff --git a/params_shard_305.bin b/params_shard_305.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8efcad5e2c86d0cbe009603039c051999faee0ce
--- /dev/null
+++ b/params_shard_305.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82daf1a8524e5de4fd766c780f40f4cf14516a8c461255ff0c5a3ed7836cfb75
+size 33587200
diff --git a/params_shard_306.bin b/params_shard_306.bin
new file mode 100644
index 0000000000000000000000000000000000000000..051a2e83d3da7ee2bd3c453fec6a667fd96fdfb4
--- /dev/null
+++ b/params_shard_306.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d47cccbc956b3992d0a2bb01e48589401bb09a75224c5f460cca63ce68fe040
+size 26869760
diff --git a/params_shard_307.bin b/params_shard_307.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cece086ed965ca1cb25c5d695a1e05d3cfd3de4f
--- /dev/null
+++ b/params_shard_307.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb79c55e9762073a0336e3fc48d74c155c8787a438d2eed600eb427f2b64257
+size 93978624
diff --git a/params_shard_308.bin b/params_shard_308.bin
new file mode 100644
index 0000000000000000000000000000000000000000..60d49b5bd5bfb8a1d1b973cf5c51460a415a9e17
--- /dev/null
+++ b/params_shard_308.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2cd90354c2034f7610929c2d48e943f888123244ca3529105bb24786f233849
+size 188088320
diff --git a/params_shard_309.bin b/params_shard_309.bin
new file mode 100644
index 0000000000000000000000000000000000000000..61e34ba5e7910f5b6353508963d061a0a2a0cb3c
--- /dev/null
+++ b/params_shard_309.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e80a2d956a94ba57945c280c13ea2c6fd12819494b174d3e17a56df44991b8a
+size 23511040
diff --git a/params_shard_31.bin b/params_shard_31.bin
new file mode 100644
index 0000000000000000000000000000000000000000..17a4df82be5cc8a7f198aca7ed4565971fe7b9e1
--- /dev/null
+++ b/params_shard_31.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0124f3f426b9c17efd4677b37d7b282c3f51bc60e27ce57dcb94dfa442cf8283
+size 33587200
diff --git a/params_shard_310.bin b/params_shard_310.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a637bd4cec9b30c0e26ae350f0a75e23e5357b77
--- /dev/null
+++ b/params_shard_310.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d0854ddca1a8a13116178d5b7760c9e790d30140dd6446c69ffe9e7111ad58
+size 33587200
diff --git a/params_shard_311.bin b/params_shard_311.bin
new file mode 100644
index 0000000000000000000000000000000000000000..266d35a73da54beb965fb175dcdd5ce4bb32e2d1
--- /dev/null
+++ b/params_shard_311.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f2be816df9912e1ab767cab686d645ef88e4a1a51f46449e79ae615e0d3f6d
+size 31117312
diff --git a/params_shard_312.bin b/params_shard_312.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0695e865b2327cb96bf74541638bb1766adcb972
--- /dev/null
+++ b/params_shard_312.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27096ec1f37bc35255fb7e487c74d63372160cf3043c24c00687ebfb993fce83
+size 31068160
diff --git a/params_shard_313.bin b/params_shard_313.bin
new file mode 100644
index 0000000000000000000000000000000000000000..968362332c58796331c8812300f0ebeee6fb65ae
--- /dev/null
+++ b/params_shard_313.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7d203370a11ec265183a6ac6f50871505e6b738bf49078a63a52b2030e93db
+size 93978624
diff --git a/params_shard_314.bin b/params_shard_314.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8b92528573f1e6b5a2d7b8092e28c1ae445d3fc
--- /dev/null
+++ b/params_shard_314.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ea789acc374275174c7326c3cb13801efa0b4031e89616d32d116a9197b245
+size 188088320
diff --git a/params_shard_315.bin b/params_shard_315.bin
new file mode 100644
index 0000000000000000000000000000000000000000..175f2d28cac4a599b70c1984ecc9d323c204fc68
--- /dev/null
+++ b/params_shard_315.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4177546366c270ba88330f5f52a2d659c633d63fb0853b107cfcccb7236bcc
+size 23511040
diff --git a/params_shard_316.bin b/params_shard_316.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a34cf564adcaf7041f5a221b5b3c62462f4d0798
--- /dev/null
+++ b/params_shard_316.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4553d22ddb3391daaea573f5df78eff806a2d5bc5d6c7447e9868112c9dfef2e
+size 33587200
diff --git a/params_shard_317.bin b/params_shard_317.bin
new file mode 100644
index 0000000000000000000000000000000000000000..61adf1f1aca5caaf85b7b0010b98845817187f2b
--- /dev/null
+++ b/params_shard_317.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8deb30f6accfe2f821f06934c85acd3ae1cf4ccbd8d33d038cf738284a3d1405
+size 26869760
diff --git a/params_shard_318.bin b/params_shard_318.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2c5a702e464d4889130624c9cba4fe2c1187a2c6
--- /dev/null
+++ b/params_shard_318.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcaf4b038d18d07ea5fa04601c7651c8a9e968d57ec2e3c78bdb734b7dadb41
+size 188088320
diff --git a/params_shard_319.bin b/params_shard_319.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5d118f212f00164752479ae14d9db606dc8b5766
--- /dev/null
+++ b/params_shard_319.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2007a84678f5ed5df78e5aa9827d39ad2218fc6af5a88699580850c922159da3
+size 23511040
diff --git a/params_shard_32.bin b/params_shard_32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7f2d58b92dd20db613e1b9b03c5eed3e23828250
--- /dev/null
+++ b/params_shard_32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529d7c9e08b48b4f687ea2226657954a1c00c6b0db611b9de44c32a82db0a979
+size 26869760
diff --git a/params_shard_320.bin b/params_shard_320.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d406886414e28cf0ada7804edc3056cf9b198b29
--- /dev/null
+++ b/params_shard_320.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9926c607383f873a07849ddf4770183356f84713f7ca65d298e667f7d8eca9e
+size 33587200
diff --git a/params_shard_321.bin b/params_shard_321.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e426d22ca51eeeef1d298da5933de60390108172
--- /dev/null
+++ b/params_shard_321.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b0cd6e8bad673015056d87f62ad1148500cc6b0f40271ba1c51a178eaecf94
+size 26869760
diff --git a/params_shard_322.bin b/params_shard_322.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b2a1cdc4c885ed71ff53fd9335e00fe786c89f96
--- /dev/null
+++ b/params_shard_322.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e4d64ab7d9ad925a5a64bcac73b48441173bd0d9d66c092ba80ca63ce91061
+size 93978624
diff --git a/params_shard_323.bin b/params_shard_323.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d7ff98f4960785bf65951b9f3f346ee08c520e16
--- /dev/null
+++ b/params_shard_323.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c95368e3a74e6cf874d1722a6cabc6c906378e178de977767c1c4b0c70f41f
+size 30269440
diff --git a/params_shard_324.bin b/params_shard_324.bin
new file mode 100644
index 0000000000000000000000000000000000000000..352e72b030abe924804b61456140d9d5b4a038e5
--- /dev/null
+++ b/params_shard_324.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b845c6ee66d2a4187db03deab39af8808776139aa8baf6ec49f2e9d74f842d39
+size 93978624
diff --git a/params_shard_325.bin b/params_shard_325.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c95b5f8f10147372874ed205aea77750a093c78b
--- /dev/null
+++ b/params_shard_325.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28cef20a4d1ca4af2f9f8ab9b02a5f6805805234fb5a32db49e6da0b1627323
+size 188088320
diff --git a/params_shard_326.bin b/params_shard_326.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9fa18c8b6baed7e1b1f1ddb9519839e4a8322c78
--- /dev/null
+++ b/params_shard_326.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e254d8967d6d0ab44aeb4d568708c2079c525dca832048310b603f36522c20
+size 23511040
diff --git a/params_shard_327.bin b/params_shard_327.bin
new file mode 100644
index 0000000000000000000000000000000000000000..94211b0acf8b4fe0e52963601915882a33f07b62
--- /dev/null
+++ b/params_shard_327.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a135da0e192d9d605246873d3d830a67b83743b64660d1262cae48c5e59fbe0
+size 33587200
diff --git a/params_shard_328.bin b/params_shard_328.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b7da4f524aae769f3e1a96f7cfe0f745799da6b
--- /dev/null
+++ b/params_shard_328.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c4b6236c340183e70ecf67a37a0748d7b4fc8cc4dabe8d05f2c8051e03dec2
+size 26869760
diff --git a/params_shard_329.bin b/params_shard_329.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c6b7f52e5131933bbc868ff5a4909d364896242c
--- /dev/null
+++ b/params_shard_329.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247a95a12901dfce1beecd1d0b107d3ef281f146a3a521e373d515b22673e989
+size 93978624
diff --git a/params_shard_33.bin b/params_shard_33.bin
new file mode 100644
index 0000000000000000000000000000000000000000..42680597bec49ce0d986da5fc12f2c169a606ff7
--- /dev/null
+++ b/params_shard_33.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e06c08835768c5bda900a338697611ebdbebfdf15d8defa1a9e46d79c027cf7
+size 33587200
diff --git a/params_shard_330.bin b/params_shard_330.bin
new file mode 100644
index 0000000000000000000000000000000000000000..19b798414879582f6c1153bba066ea64e2b8a833
--- /dev/null
+++ b/params_shard_330.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffb085ebaa4253c66086e5755a2ea74c848006189529df522ab7336d9aef3d2
+size 31117312
diff --git a/params_shard_331.bin b/params_shard_331.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e32350844a5144e1e01444c8bdac91087a0e1324
--- /dev/null
+++ b/params_shard_331.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54b8f5bc2d7e788f6eca1bb90aeccdab417a52370a176afacbd0f2d77ac1f34
+size 188088320
diff --git a/params_shard_332.bin b/params_shard_332.bin
new file mode 100644
index 0000000000000000000000000000000000000000..60e2c15ca1c10e0989b7f0da03ab3ff55ac8df79
--- /dev/null
+++ b/params_shard_332.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7b1c93761f82735e135942e6d4ea3effae69ccab293534f33bd7ba8f1b0d6e
+size 23511040
diff --git a/params_shard_333.bin b/params_shard_333.bin
new file mode 100644
index 0000000000000000000000000000000000000000..451f167bf1525875f2ae061d04f21caeebb5aabd
--- /dev/null
+++ b/params_shard_333.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ae7572b38d094adf99d7ee7ad9837859796a1615187a2bbcc59f41fe74c977
+size 33587200
diff --git a/params_shard_334.bin b/params_shard_334.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e1d14b193cc108572e9a805559af489438099cf9
--- /dev/null
+++ b/params_shard_334.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72591c29c7a5f19ed56c846b7b849be5780c7146cc119e63cb8339636cb876f0
+size 26869760
diff --git a/params_shard_335.bin b/params_shard_335.bin
new file mode 100644
index 0000000000000000000000000000000000000000..641ab0741f928ea519dec263981a9dc448460bcc
--- /dev/null
+++ b/params_shard_335.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb988a2a92d70ddb066f4ef7ccaf9ed0881e26c71c598777bcfaa896c0aaccbd
+size 33587200
diff --git a/params_shard_336.bin b/params_shard_336.bin
new file mode 100644
index 0000000000000000000000000000000000000000..80cb3871ed380bb7fa1ff66fdd80928c3c6e2d1c
--- /dev/null
+++ b/params_shard_336.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b44a13fc94216c89a8cc7873524ee93d3e4d353afb25a34e7fab25e9d92a8e3
+size 26869760
diff --git a/params_shard_337.bin b/params_shard_337.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ac2ff08550def5121f800c2bd5a933b950a27595
--- /dev/null
+++ b/params_shard_337.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0260fcf996aee88f661e2714c97114fd5444cf2a45d548bb8843dcee4a309b
+size 93978624
diff --git a/params_shard_338.bin b/params_shard_338.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4596f851fca6b1e530a0006533e6383588fddab0
--- /dev/null
+++ b/params_shard_338.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a62abcc9f643faff0c40f3d4fd4cc307ad1a1f592ee03904a2c84cb39e7fcd
+size 26927104
diff --git a/params_shard_339.bin b/params_shard_339.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0a2d5500c272fbdf1e020b4a0d12970c82099e1c
--- /dev/null
+++ b/params_shard_339.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542b94e530358a92965c3355c546f79fbcc01410c31eae4eb94e47dde7dfa2e4
+size 188088320
diff --git a/params_shard_34.bin b/params_shard_34.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d3ad25ed6b383aa0768404bd931d87213df7fe3
--- /dev/null
+++ b/params_shard_34.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed4aaa297fa60ecb618c17a37c10dbb553794ec3ef7ad2e5ba50881a272f2eb
+size 26869760
diff --git a/params_shard_340.bin b/params_shard_340.bin
new file mode 100644
index 0000000000000000000000000000000000000000..44b5a16394cc453e009ad81d5ce62bc59f7d318f
--- /dev/null
+++ b/params_shard_340.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cb0e2c29b4485c286280dbefd6d3339a8e4200946baf27fcea64b920a2946d
+size 23511040
diff --git a/params_shard_341.bin b/params_shard_341.bin
new file mode 100644
index 0000000000000000000000000000000000000000..95a98a723dddd9e8baeb09668fb28ffe3d78baf4
--- /dev/null
+++ b/params_shard_341.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b622e7fc0ee356fe6bdb38140926d8bccf9c63b50b8ba8887687e9dcb787608
+size 33587200
diff --git a/params_shard_342.bin b/params_shard_342.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f3c1e5bb68376e4de44b692e0cca725e5e898f8
--- /dev/null
+++ b/params_shard_342.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731f3911d8fbfeb5a005637755c2069c82b83e8ae88940a5b95d210ee4c00b6f
+size 26869760
diff --git a/params_shard_343.bin b/params_shard_343.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5fba41381b45a3228cb7b3851ea22aad48fe1cc9
--- /dev/null
+++ b/params_shard_343.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b272131e7cc9d2b3c3a7199e275c7deddcdaa531652c0d4ae140ef8adbbe8b
+size 93978624
diff --git a/params_shard_344.bin b/params_shard_344.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cba1228b7675c5302866b2bde3d2b8adf50b7513
--- /dev/null
+++ b/params_shard_344.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b8fccd49da6c1644616b1406173f79b7d1420735dcb3c2d0cd7c4925e56449
+size 188088320
diff --git a/params_shard_345.bin b/params_shard_345.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f3b66df105686329be596dffdc92e4273b4169d8
--- /dev/null
+++ b/params_shard_345.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161456321aa4cc1650a8b0fff8fca25c4c9dd2616e12f4d535157cb67b16bd6e
+size 23511040
diff --git a/params_shard_346.bin b/params_shard_346.bin
new file mode 100644
index 0000000000000000000000000000000000000000..774911543b19d3fb3b0096d09200fdf5259cba22
--- /dev/null
+++ b/params_shard_346.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af952eb887e7e9a6bfaeb21779999e19993c06e7a93d1e500e1c3e308a4f28d
+size 33587200
diff --git a/params_shard_347.bin b/params_shard_347.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d4b654ca3dab565ed2571b435a0e13d1ffc23b5a
--- /dev/null
+++ b/params_shard_347.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b411ad145650bf0a1ee39dde2ee15f902680a41fb9c80e1c6131067584f533a8
+size 31100928
diff --git a/params_shard_348.bin b/params_shard_348.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e8b1b22d36a8d333a9ddf9c736bb324644ffb6c1
--- /dev/null
+++ b/params_shard_348.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18533d5ff157a2804a0925f7aaccb8e13b50e6148039b075898bf9e10316eada
+size 31068160
diff --git a/params_shard_349.bin b/params_shard_349.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e9759ec77fef9965783a641397288160c0634f50
--- /dev/null
+++ b/params_shard_349.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d5ef17800e2794e273ff100b821f268fc12a667a96a26c7c98e8164e72875a
+size 33587200
diff --git a/params_shard_35.bin b/params_shard_35.bin
new file mode 100644
index 0000000000000000000000000000000000000000..09179f6b4ddf393a40fb864c838509734f7af855
--- /dev/null
+++ b/params_shard_35.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4577ecb4a09c03d5bc43e338161e2e923443120b4220c3d1e5d25002f8ce65b5
+size 93978624
diff --git a/params_shard_350.bin b/params_shard_350.bin
new file mode 100644
index 0000000000000000000000000000000000000000..42730c7885a736bf0b13086914eef61f04468b0b
--- /dev/null
+++ b/params_shard_350.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cb301b573eaba01206ca7ab5dce262143058bfbfc55c472899bf056e952980
+size 26869760
diff --git a/params_shard_351.bin b/params_shard_351.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a30caff263ae11168725b3bd2e936eeee64e29b0
--- /dev/null
+++ b/params_shard_351.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01715825fa621a8d6a70e4d9b91f4f70584344454cb0ff8885f26441f437927
+size 93978624
diff --git a/params_shard_352.bin b/params_shard_352.bin
new file mode 100644
index 0000000000000000000000000000000000000000..265743eedd617303f68b5cf7ba8d667c6bfd5e5d
--- /dev/null
+++ b/params_shard_352.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b18d1bec2547ea8b8f41c775e8a6c9c1b6ceea885ecd978325d591fa36d979
+size 188088320
diff --git a/params_shard_353.bin b/params_shard_353.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d543d6c9162db135e5b5ec64c9c0f4a9436fc15f
--- /dev/null
+++ b/params_shard_353.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2401c3dbbd8f17b504662065781d410a740495fcf822e25b395a7bd127f1fd
+size 23511040
diff --git a/params_shard_354.bin b/params_shard_354.bin
new file mode 100644
index 0000000000000000000000000000000000000000..654a3ebb097fd851ee3a2ca2cff71eb7eafcce0a
--- /dev/null
+++ b/params_shard_354.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ea5b822ab04cabb2a75f756366d1786e4dd6164611d5cac4cbd5a77b316440
+size 93978624
diff --git a/params_shard_355.bin b/params_shard_355.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7d2a84d5bc817d766683cf8e1036d3b49a73c369
--- /dev/null
+++ b/params_shard_355.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1b859bfb542d402ee2b1ad0f24882b3aa7de29d46c0653cef4c6affe6b6794
+size 22712320
diff --git a/params_shard_356.bin b/params_shard_356.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e610ebac6dba129ab2165602d86d07518ccc8c01
--- /dev/null
+++ b/params_shard_356.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2145c7d08cc6081890d2562456c8dca96b7237d0cbb41736447fa3992d8c096
+size 188088320
diff --git a/params_shard_357.bin b/params_shard_357.bin
new file mode 100644
index 0000000000000000000000000000000000000000..32ae886915c8ee8eb2146fedc79006f22d629b9c
--- /dev/null
+++ b/params_shard_357.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc633f70568bc6e2ed0252c2fc6fd99958f23d4536fab173b02a9377b1f765fd
+size 23511040
diff --git a/params_shard_358.bin b/params_shard_358.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9e548a14d7f692e860e589a49fbdb5c32c269d15
--- /dev/null
+++ b/params_shard_358.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c33ebe0dd3d96c2f35d967f012510db79d8d0fff461c20824d3bc68abdc088
+size 33587200
diff --git a/params_shard_359.bin b/params_shard_359.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2c15f03b892c6f73ccaf52192fceebd2ebf564e3
--- /dev/null
+++ b/params_shard_359.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab38e8e72e5fb1a5721e262dff3e07313a34ff8808fc9b899f26f4589e6901f6
+size 26869760
diff --git a/params_shard_36.bin b/params_shard_36.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9330ededb0a1da78e794f85cf36a03938b0f1b4c
--- /dev/null
+++ b/params_shard_36.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd77df5dea575992eacc3a9d3860b21a4a8197aa791e32368757bcc02ec344a
+size 30269440
diff --git a/params_shard_360.bin b/params_shard_360.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65e9bb00c6cb865024b8b8e2276a50cd63d9aee5
--- /dev/null
+++ b/params_shard_360.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863af324f1f4256ecb5441202bb6d7b59e5b2b4032522db1e136f5d9d13a1a55
+size 93978624
diff --git a/params_shard_361.bin b/params_shard_361.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5fa11e45f305202bfb06f33295f4df6548b009d1
--- /dev/null
+++ b/params_shard_361.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7003766d9265f8b8753bed0943b0e491650a27befaed8e52a023d81e588973
+size 188088320
diff --git a/params_shard_362.bin b/params_shard_362.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b64d191530aae384f77961ad66a15827ef93bd59
--- /dev/null
+++ b/params_shard_362.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0688fd8149b381759bc1a77321fbd99cc1a78cf04e244e4d82a904b7fba01a
+size 23511040
diff --git a/params_shard_363.bin b/params_shard_363.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d338f5f713ed66330b8e0813f8823840728f8b28
--- /dev/null
+++ b/params_shard_363.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47246c50f1630167cad0b143f375e5ee9fe0c19d3cb7ce56ee8983fa488ca02
+size 33587200
diff --git a/params_shard_364.bin b/params_shard_364.bin
new file mode 100644
index 0000000000000000000000000000000000000000..808da9bb9e8131ee03fa22b26e7fac1a2306b547
--- /dev/null
+++ b/params_shard_364.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169dbe058de4995ba33c38058333e0227e6bfa00636ab74d7069b26860ea0c55
+size 31068160
diff --git a/params_shard_365.bin b/params_shard_365.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c19494e1ba21466c319f9034c505f719b5e20b62
--- /dev/null
+++ b/params_shard_365.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8c190bccbba5939d3540024cc2235b44b7f0222b0b05216592f819a2b87082
+size 31068160
diff --git a/params_shard_366.bin b/params_shard_366.bin
new file mode 100644
index 0000000000000000000000000000000000000000..582c0a47d3a1eef515ce60f299e5f26c6b0addae
--- /dev/null
+++ b/params_shard_366.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e87a74f2d31bba6df7128daab3baeff914079fd3f98deb533d17ec1fd37b31
+size 93978624
diff --git a/params_shard_367.bin b/params_shard_367.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5025c7da4a0c90c8ff5ee443a2cc868768618a1
--- /dev/null
+++ b/params_shard_367.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884b6e6e5d9aa29b1264d4d926abe34269786ee4133415b923d6be087b75c8fb
+size 188088320
diff --git a/params_shard_368.bin b/params_shard_368.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7515c78d87e6ef4c63be05b0f340045784555b40
--- /dev/null
+++ b/params_shard_368.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cfefd1d9497399096bd2b93f03fbb5eeb89f88a38f73bbe7dbb1c48114c62e
+size 23511040
diff --git a/params_shard_369.bin b/params_shard_369.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5e4858a4ec2f150807674bb64d531725de07952
--- /dev/null
+++ b/params_shard_369.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99196cdcfe63fb4c45bcbf4eaf4e3656c68735216ad80e8043b245e46ab1647d
+size 33587200
diff --git a/params_shard_37.bin b/params_shard_37.bin
new file mode 100644
index 0000000000000000000000000000000000000000..617d790570d1b94ab4c30dcda1ef0d2f394bcb1f
--- /dev/null
+++ b/params_shard_37.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01136a8819f634bfa1b6c3845f3a213996daadd5d36dc0954f2c0845cc6fe7cc
+size 188088320
diff --git a/params_shard_370.bin b/params_shard_370.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fd0075a35a5a2646a871561768be628cdd16c1e0
--- /dev/null
+++ b/params_shard_370.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de134c0f2a253fe70ffda622e880806770dec09c498259e197381c3bc268ab0c
+size 26869760
diff --git a/params_shard_371.bin b/params_shard_371.bin
new file mode 100644
index 0000000000000000000000000000000000000000..78e9d3265c68f3562f8e6dba2823411275a282ad
--- /dev/null
+++ b/params_shard_371.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbeda3d2d9fa62434e53bc14e2622b9310147aadfd65ddda64faa4cc68d7ba3c
+size 93978624
diff --git a/params_shard_372.bin b/params_shard_372.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e2847d7c4918c338e2744df891d2f2677a61bd9
--- /dev/null
+++ b/params_shard_372.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d485e804c41aa9b4ddc94aa003debca8f8cc46f7fc7482b8d02a7490a9bdce5b
+size 22745088
diff --git a/params_shard_373.bin b/params_shard_373.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c5ba57c4f56618c8b4d56e10ba57182a3b012ae0
--- /dev/null
+++ b/params_shard_373.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1be45234555dbfec5cc16dfa285fd5d8862c3a6c771241f6bebb4832af561cb
+size 188088320
diff --git a/params_shard_374.bin b/params_shard_374.bin
new file mode 100644
index 0000000000000000000000000000000000000000..59acc9677d8acd623d6fa01de6d9113cb0e8b22a
--- /dev/null
+++ b/params_shard_374.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03065b2a0dfb55b4d1114df290c96209ce80a719582740b33206319f1bf52469
+size 23511040
diff --git a/params_shard_375.bin b/params_shard_375.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e719e479dc6c9bcdbed29e6634079cd7739ad9e5
--- /dev/null
+++ b/params_shard_375.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3213c984d15a871a02c09b0250e55ba49ccdca304fc9548681fa26ce6908f43
+size 33587200
diff --git a/params_shard_376.bin b/params_shard_376.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c871be11b15baf81a5bb7bff3a89fe76da3c110f
--- /dev/null
+++ b/params_shard_376.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c387e0208ccec3075da963489af8d310a5429648ae0fda6999ba0c1a16c26a
+size 26869760
diff --git a/params_shard_377.bin b/params_shard_377.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e31ea41c962d717c747e083ca19aca81134ab8c0
--- /dev/null
+++ b/params_shard_377.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3f326e69e50c4b57d5cdd960ee11b06fe112c99f4145df453e448fec0a7528
+size 188088320
diff --git a/params_shard_378.bin b/params_shard_378.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9dc01388a083182a248a526bb6e9aa39af53c53c
--- /dev/null
+++ b/params_shard_378.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fde298c7c8cf39ff59b0ed06be3209f7757f42da49e697a372975b80e20a55
+size 23511040
diff --git a/params_shard_379.bin b/params_shard_379.bin
new file mode 100644
index 0000000000000000000000000000000000000000..367b049d2bbeda53c88ff134f4ea35b3f96b00cf
--- /dev/null
+++ b/params_shard_379.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6798dbce37b2deef6ccce06d404efabe440868aa3168a358f667a3e515257e1a
+size 33587200
diff --git a/params_shard_38.bin b/params_shard_38.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f327ec07d9af8c535c8d02d35a27d123cb48217e
--- /dev/null
+++ b/params_shard_38.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d4de2a494163876c87725b8ac1670701229541e9ab2ae2d330e9952e10ba5e
+size 23511040
diff --git a/params_shard_380.bin b/params_shard_380.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f97ae8ddcdc38ec03cd3e3150be8b7e14bb45fb5
--- /dev/null
+++ b/params_shard_380.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b56834cb25793ed4162309585fbae180b81cb4aee63890ba5bd7bec90c5407
+size 26869760
diff --git a/params_shard_381.bin b/params_shard_381.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e83bbc22b1725ea94ff232751dc89fbb38508417
--- /dev/null
+++ b/params_shard_381.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83d2e4821ffc46433500fa5ed546d7fba0299d64e920043d188c3b6c07eeb75
+size 93978624
diff --git a/params_shard_382.bin b/params_shard_382.bin
new file mode 100644
index 0000000000000000000000000000000000000000..96cefc86c57e2efc0c06b6458e26cfe7dbd003ac
--- /dev/null
+++ b/params_shard_382.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71db833a2bd5cf3093fc6d8e8f3f14948a9161a6dc68ed396feddcfcc920f2be
+size 26894336
diff --git a/params_shard_383.bin b/params_shard_383.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e6d7bf4b1cf73cf9322d4b8f103a7aaac7967247
--- /dev/null
+++ b/params_shard_383.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdde620ca0462706bf81bb91f72934ef0741810ffdb6ce2dbd1a4bfb9d81edc
+size 93978624
diff --git a/params_shard_384.bin b/params_shard_384.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9a1752f2b63f163633fd23b398a2a687f8feb477
--- /dev/null
+++ b/params_shard_384.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8080a16084f7c51057f6fa1de2d1454e81233bcd5392a59a1ca510a1e60d6621
+size 188088320
diff --git a/params_shard_385.bin b/params_shard_385.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bc6ceae86ee4e39947bf5a6f810fae6d88db6c7e
--- /dev/null
+++ b/params_shard_385.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70252fa7a11a6a4784f993932f2909d4ee01a7d9e21d759f2a7fefbf64ea7063
+size 23511040
diff --git a/params_shard_386.bin b/params_shard_386.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6eec7bd88cf43f2770462f6a455f086c00aa03f2
--- /dev/null
+++ b/params_shard_386.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e4c7226dfa91dd597c5d6e77881af59c7c35bceb88fbab264709f24224f992
+size 33587200
diff --git a/params_shard_387.bin b/params_shard_387.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da5e3220fd38bff050923e7cef43d70aef26721d
--- /dev/null
+++ b/params_shard_387.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af57679170a093d7828a5c65f93290d5bc649521181770698f1202e21a377682
+size 26869760
diff --git a/params_shard_388.bin b/params_shard_388.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5953f9dc017108a29e4d9214fdd3823a531c1bf6
--- /dev/null
+++ b/params_shard_388.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c09d0cef59aea26e46d493e9bb00977d23dc9dc43f1ba7db25d8229b584a2ce
+size 93978624
diff --git a/params_shard_389.bin b/params_shard_389.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5cf729d3c5d3293a4bd21e9c45ec5f2a3efd3860
--- /dev/null
+++ b/params_shard_389.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b57662ad42694f916da246532c572c821d0ce9001e6d5a79bf6328420c7b86
+size 31117312
diff --git a/params_shard_39.bin b/params_shard_39.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2e9a49164e6c58e7d2929ee9a689853ea3d3d9d8
--- /dev/null
+++ b/params_shard_39.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c881536f57bf1e3e7b9cac0fdbe80cc1f269a0df7d246b292d308be54dac486e
+size 33587200
diff --git a/params_shard_390.bin b/params_shard_390.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5e2fa20989e766099fb217566ca1ac11223091f0
--- /dev/null
+++ b/params_shard_390.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4dc88bdaa57565e6d95f57d6b529e591ce4f6a43e6e0c2e4b6161a1d852046
+size 188088320
diff --git a/params_shard_391.bin b/params_shard_391.bin
new file mode 100644
index 0000000000000000000000000000000000000000..73402ff946e886f0fd11a02b20467cf52685a378
--- /dev/null
+++ b/params_shard_391.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da9f3e05b09baa0c7d74161cc04e23b306f3fd4bdd7a9d7cdd91e732a00026e
+size 23511040
diff --git a/params_shard_392.bin b/params_shard_392.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da09830548f1bfb588a74dd9c280ae62d38541df
--- /dev/null
+++ b/params_shard_392.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1d3b6946612569ae3698476a55f1ecab0f5e750d5a9ef647e02f0deb74a6c1
+size 33587200
diff --git a/params_shard_393.bin b/params_shard_393.bin
new file mode 100644
index 0000000000000000000000000000000000000000..49fcff2aed4200e6f8fe77bf1a1c426719ca097a
--- /dev/null
+++ b/params_shard_393.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4cda0ba28a5ee171fb3c87678b22afaf3b59dcc2e0a7c0e98bb3e4f7f5a00c6
+size 26869760
diff --git a/params_shard_394.bin b/params_shard_394.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ff74df0e3cc56ff823f52ce4d2eb8477800d8edc
--- /dev/null
+++ b/params_shard_394.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554b41cf7764ac82aafb6c1af84c888008f75acfe34500593feb28d32ca0517d
+size 33587200
diff --git a/params_shard_395.bin b/params_shard_395.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e972bd675d0698c3cd8124be24027af08d455cee
--- /dev/null
+++ b/params_shard_395.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b4b0cedb09f37878543c9f2604dea9d7e5af6cc0b868c2fe0b2ac06cb7de51
+size 26869760
diff --git a/params_shard_396.bin b/params_shard_396.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cb4fee68a24248936eb6cb2686572561cc59642b
--- /dev/null
+++ b/params_shard_396.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41160d8b316135b82a8f7dddeb57413264dd0d73343171a2ab1ae3220fda6a2
+size 93978624
diff --git a/params_shard_397.bin b/params_shard_397.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0773edc9609c205857ef09eaddf6bdd5a3c5a9e7
--- /dev/null
+++ b/params_shard_397.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db1c3f7804a7c28ee6bd7782639a7e17d6f3b33fa9801950449155968d83bd6
+size 26894336
diff --git a/params_shard_398.bin b/params_shard_398.bin
new file mode 100644
index 0000000000000000000000000000000000000000..733bf4cc070802721c6d78b2303318e5765640a0
--- /dev/null
+++ b/params_shard_398.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb86f5b09c1c7013d8cd454a5eebf93456878ea4969ef96046af4902119e8dc2
+size 188088320
diff --git a/params_shard_399.bin b/params_shard_399.bin
new file mode 100644
index 0000000000000000000000000000000000000000..050652ed44ab855db16915c0549133d87fba76ad
--- /dev/null
+++ b/params_shard_399.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f42973464041094db1f2907a6e93dd61ce7cfcdf76013b147de0eb51c975db
+size 23511040
diff --git a/params_shard_4.bin b/params_shard_4.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8db8c0857b0c9fdddd7db7cbd182aa8b264399ac
--- /dev/null
+++ b/params_shard_4.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237985a04cb3e0bbe627f63d877c115eaa752c4665b26a3f12a011ec923964b1
+size 23560192
diff --git a/params_shard_40.bin b/params_shard_40.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7eec1bcd94d5a7630cf5000839d49fcfe1fef779
--- /dev/null
+++ b/params_shard_40.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e333775ec8a3764014ad603e84a44e117e3844c782f402f8d3e7784a09e416
+size 26869760
diff --git a/params_shard_400.bin b/params_shard_400.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dc0b98c1a35c726383d16c48c88dfc45b3dee846
--- /dev/null
+++ b/params_shard_400.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11384ad5edb3f5a9132b54026c7406bc114836c95ebe7d2242fd5c7a855bff02
+size 93978624
diff --git a/params_shard_401.bin b/params_shard_401.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c1d95c73085d2af880d6bb82dd8b5e637f9de578
--- /dev/null
+++ b/params_shard_401.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f057b7569887c3092d78514546b57d781c21fcaf0c884e4b7d4fab1d7f2420a6
+size 188088320
diff --git a/params_shard_402.bin b/params_shard_402.bin
new file mode 100644
index 0000000000000000000000000000000000000000..abb2c962f4f477dd56dfe43768c91b8538ef165d
--- /dev/null
+++ b/params_shard_402.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ab6a72d87b6388d703cb60cf063cd95cff13cd842d2a6b2ee40d4029700346
+size 23511040
diff --git a/params_shard_403.bin b/params_shard_403.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f74ad2ae91bc470c270eda486c52a3b122068f83
--- /dev/null
+++ b/params_shard_403.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a86e086e48d87f0b6450c96526ccd85456a2818a53f908f1222b018a50a2b0
+size 33587200
diff --git a/params_shard_404.bin b/params_shard_404.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2c90086449c05629126c48f25153e7fd5cd41610
--- /dev/null
+++ b/params_shard_404.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595cdf2e9c277a31f4aa5b9d575842597b4326bced78d442c136ab07264bcd88
+size 26869760
diff --git a/params_shard_405.bin b/params_shard_405.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ae0cd60a38bd178672aace11ee4c9bc45b848906
--- /dev/null
+++ b/params_shard_405.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bbfc3057f5f6e27120248ed4d051819afe986901c922407a195f91334dded1
+size 93978624
diff --git a/params_shard_406.bin b/params_shard_406.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eaed0ea4a1527923ca73f37a19ef5d1304c6cf61
--- /dev/null
+++ b/params_shard_406.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9534c47575ebf66624dae0dce038239b7702f651f34602f3020e0e842b594ae
+size 31100928
diff --git a/params_shard_407.bin b/params_shard_407.bin
new file mode 100644
index 0000000000000000000000000000000000000000..33152915fceebb3a3abcc2618ed375016f899900
--- /dev/null
+++ b/params_shard_407.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782e9b84ef4f4d841a8b23f3c5d1cd57d0350917a1410c4066de0f1b5a591843
+size 188088320
diff --git a/params_shard_408.bin b/params_shard_408.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1cb307cf269a1eb69dfb74bc0077e19dd3ca5d49
--- /dev/null
+++ b/params_shard_408.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82d5a4ab3529c09145ba5208c988981ce699e6b5e8537d81bee0d37cdab30b2
+size 23511040
diff --git a/params_shard_409.bin b/params_shard_409.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c48220f606e87f9b2323e605e6ea387f93bda7e
--- /dev/null
+++ b/params_shard_409.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c86adfd748d4b7c0797f48b522aca1f7733aefcdd8b2bafaffcb25eb21c86e8
+size 33587200
diff --git a/params_shard_41.bin b/params_shard_41.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a9d45c9ec5d7ee3c5b17b66c3a6b03e57fba64b7
--- /dev/null
+++ b/params_shard_41.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6760bf89c4a643fff5d53bc7a96019df3951ddb21d7e3269d3dcba97c88a1dc5
+size 93978624
diff --git a/params_shard_410.bin b/params_shard_410.bin
new file mode 100644
index 0000000000000000000000000000000000000000..493eef5ea5961dbf64232f67e5de4d80e9b4ca71
--- /dev/null
+++ b/params_shard_410.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c801d55d1eeec32e283f6dbc33a45db935f32331e545dd0fa6f9e128fa31542d
+size 26869760
diff --git a/params_shard_411.bin b/params_shard_411.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7ac5695d9ff3df08de558c090e20696f7f90acdd
--- /dev/null
+++ b/params_shard_411.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6f2159db9ede36331ab1d5554ba2e9de11438d71341efe1f993ade52033449
+size 93978624
diff --git a/params_shard_412.bin b/params_shard_412.bin
new file mode 100644
index 0000000000000000000000000000000000000000..10e0f64914658290c6c31637c75af8b31ca9c107
--- /dev/null
+++ b/params_shard_412.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac18008140b96e7d4b1a66501032f2876ff13326794f4c816d72bac5ef27cc3
+size 188088320
diff --git a/params_shard_413.bin b/params_shard_413.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6689e680425fb8ff0e4563ea40983f0c400e0ca3
--- /dev/null
+++ b/params_shard_413.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9301ecf38e16993eb9cd1cd97a6867598c3ae1d2d95077c125e0d621d336d1f
+size 23511040
diff --git a/params_shard_414.bin b/params_shard_414.bin
new file mode 100644
index 0000000000000000000000000000000000000000..54e1654ea7882d715552e3f63a988e674ab908d6
--- /dev/null
+++ b/params_shard_414.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92071bc3889eeb850d401e9ddeaacb5b264c074190ba3bc8805c1055725194be
+size 33587200
diff --git a/params_shard_415.bin b/params_shard_415.bin
new file mode 100644
index 0000000000000000000000000000000000000000..724eec2a8377faaa48a7377d244053dba8d03bca
--- /dev/null
+++ b/params_shard_415.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc397608ecd385a8120386ccffa42d95a4abc9167eb62615386b709d1d4f930
+size 31117312
diff --git a/params_shard_416.bin b/params_shard_416.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f3f3ffcef976feeba04457734dfb222be4c8e535
--- /dev/null
+++ b/params_shard_416.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2585633dc9d318c5d6b52587bbbda57c8c72c58aca9de4ae422c64fce390d34
+size 31068160
diff --git a/params_shard_417.bin b/params_shard_417.bin
new file mode 100644
index 0000000000000000000000000000000000000000..50156e819679220f5e6405af86460a7bbd7060a7
--- /dev/null
+++ b/params_shard_417.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9d72a763b3698cdc53cb35f35eb1b935b4834e8c5383f26179d21bc2d1de42
+size 93978624
diff --git a/params_shard_418.bin b/params_shard_418.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0bf40737813f5a290aac7476176714dcbfbb64d5
--- /dev/null
+++ b/params_shard_418.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496c4335b3a00d2844d36bbb9ebd7c9cfb815b1daa6079dc6751b65a92ce02c1
+size 188088320
diff --git a/params_shard_419.bin b/params_shard_419.bin
new file mode 100644
index 0000000000000000000000000000000000000000..18f6e55bff4808f02b4b8ed975e21d12515a2861
--- /dev/null
+++ b/params_shard_419.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b83427a2dad5d2bd77822211fe8055f602ecf662b01b06230418db2cba80225
+size 23511040
diff --git a/params_shard_42.bin b/params_shard_42.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b1657e5f90c8daa403c8ef4db1e9fcd7a8d0d481
--- /dev/null
+++ b/params_shard_42.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4ae039b50dac2158af7427976f41923e52b8955b0dcf843eb7706bb6e27e5a
+size 188088320
diff --git a/params_shard_420.bin b/params_shard_420.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7aa9e441e9f1d5c90c1c03c719313b57a59592dd
--- /dev/null
+++ b/params_shard_420.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3dcf712753660c4ef3e588c7617422fe733bc3abbe75be8d65bb8931b3aadc6
+size 33587200
diff --git a/params_shard_421.bin b/params_shard_421.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2d6608878b20a2182bb9a76802a44761de7589fa
--- /dev/null
+++ b/params_shard_421.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6584ffc225fbc21cac8f47faedc699d443280009e5b536228b1bab5e3acb258
+size 26869760
diff --git a/params_shard_422.bin b/params_shard_422.bin
new file mode 100644
index 0000000000000000000000000000000000000000..454060107a6b6b1248c5a2905eb8d2aabfc07648
--- /dev/null
+++ b/params_shard_422.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856b3cde722a38e3f3e9cb8eebed701166c8224561855bbebd4124950087b9f3
+size 188088320
diff --git a/params_shard_423.bin b/params_shard_423.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5382f50161e9444f5b3ae3e9585c38e8d498a53b
--- /dev/null
+++ b/params_shard_423.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e0a3b99c61166f8452b670a2d41d9e8a788b1aa17c23967951fcf74e6547fb
+size 23511040
diff --git a/params_shard_424.bin b/params_shard_424.bin
new file mode 100644
index 0000000000000000000000000000000000000000..46a711c1eb3839cb50f1ddd12732bf954b86a428
--- /dev/null
+++ b/params_shard_424.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6556b6b67916fd314d44f166711df575e65f24cd8ce746615b2e768182c910
+size 33587200
diff --git a/params_shard_425.bin b/params_shard_425.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8012fad24c5e7e0df6193acf4c1babb247101cde
--- /dev/null
+++ b/params_shard_425.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586011de673b7d393ca73af2e17495d2880ba0c62b4ffa2baf0737197dc0cc58
+size 26869760
diff --git a/params_shard_426.bin b/params_shard_426.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1b17dfb0833ba5c704b5107ec973a5b972781e84
--- /dev/null
+++ b/params_shard_426.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e60f8389c882afa44d0c1a99457e3aa1158bda67feeadfd85d72a6c0fdc7da4
+size 93978624
diff --git a/params_shard_427.bin b/params_shard_427.bin
new file mode 100644
index 0000000000000000000000000000000000000000..36a939ed660dd9fd7c67261cb94d4179bd7c9b5a
--- /dev/null
+++ b/params_shard_427.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7620c277515cecc912b3c2f05312f1cea196a132c8f855b09714fc991ea688b9
+size 30269440
diff --git a/params_shard_428.bin b/params_shard_428.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c72bc1c00eb1a2561a09c2dfe464849c21a04f7
--- /dev/null
+++ b/params_shard_428.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed472aa5028dd4626c76fe5d7c53486a7bf378abd875869de8832e6c93869865
+size 93978624
diff --git a/params_shard_429.bin b/params_shard_429.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8bc865a45218e02cdd41a9c2a2cb323373987763
--- /dev/null
+++ b/params_shard_429.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78954bb87fab12dfb75b9e6908f796ea5c0cfbb0fc78b12b0d8afac60a9c5c1
+size 188088320
diff --git a/params_shard_43.bin b/params_shard_43.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5f31f1774b7993b83074239b38b11e2ca33b9257
--- /dev/null
+++ b/params_shard_43.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc1ecd9f4db89162c32f6b956af9388874d73208f0d37fd9f57fc10ab1e3b50
+size 23511040
diff --git a/params_shard_430.bin b/params_shard_430.bin
new file mode 100644
index 0000000000000000000000000000000000000000..629bf1ab7faecd7f69086eb1db5dd31503528359
--- /dev/null
+++ b/params_shard_430.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d912da6c313cae66cd27f1e2a06872750db0da796c44c5bb6485bb0ca485922
+size 23511040
diff --git a/params_shard_431.bin b/params_shard_431.bin
new file mode 100644
index 0000000000000000000000000000000000000000..380bc993bb736ac182d18031b3428e031953115c
--- /dev/null
+++ b/params_shard_431.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa960101414597ecea52611313c9bd78ced7d3595cb0a7f865a643587d03d40
+size 33587200
diff --git a/params_shard_432.bin b/params_shard_432.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b425c67f500a1d9dd57b2eaef3c2ec8b247c546
--- /dev/null
+++ b/params_shard_432.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a5cc650f8529400e8d7409884558594ef06570f1b4f568feb9e38f4355416e
+size 26869760
diff --git a/params_shard_433.bin b/params_shard_433.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8232675509dd277923aba4cd671c3f83f69ae932
--- /dev/null
+++ b/params_shard_433.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7241b06c90897daf9f6bc81f7c1c188915c7c0013fa96199630723b4d8ede07
+size 93978624
diff --git a/params_shard_434.bin b/params_shard_434.bin
new file mode 100644
index 0000000000000000000000000000000000000000..835fd4d989d52f126ec55bdbf7ae6d859f503728
--- /dev/null
+++ b/params_shard_434.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9219b68007a5cde27f447830a6d30a993d6ae228f6b037ac0cd75e5002671ab7
+size 31117312
diff --git a/params_shard_435.bin b/params_shard_435.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9d246241d549430c010386ff32833cc5bcb3401e
--- /dev/null
+++ b/params_shard_435.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd04b899eb3525fdbf8e32c81f77a53b0dffbc5137cb2c01701458469079362d
+size 188088320
diff --git a/params_shard_436.bin b/params_shard_436.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c391950e60c67de6e2c3100e446875b73f45ee5a
--- /dev/null
+++ b/params_shard_436.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6eb604cfae4bd39b9f4c25b455d6824d2e5f1458b80ebeac28e1780d695d058
+size 23511040
diff --git a/params_shard_437.bin b/params_shard_437.bin
new file mode 100644
index 0000000000000000000000000000000000000000..06c8a43b25b4a9af24facc8fadb8a471bce61112
--- /dev/null
+++ b/params_shard_437.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c56a9c9894fa074fff25725f7c7ec5d0fb3281bebbefce9043f77a5e33b6b9f
+size 33587200
diff --git a/params_shard_438.bin b/params_shard_438.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e63be5c837ba2a0c2abc4fa26afa763369f64c7e
--- /dev/null
+++ b/params_shard_438.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f89dd4d5db8eb9ae7a1d625c39a6c845e10112c37285fa8c10a22489a922fc5
+size 26869760
diff --git a/params_shard_439.bin b/params_shard_439.bin
new file mode 100644
index 0000000000000000000000000000000000000000..569f26ceaaf11b708774f05df527c73ebd0d8770
--- /dev/null
+++ b/params_shard_439.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4fb733fa68bead76b9e4f4ecdc7fc76a8a727290d9e43239c08b827a6feca9
+size 33587200
diff --git a/params_shard_44.bin b/params_shard_44.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a21769eaf29ab489d5de81a594d84e93e142320b
--- /dev/null
+++ b/params_shard_44.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f74541907f5ed65c6690112ff4a93c524e77b5abcf2e1f134d9d9db49a3688
+size 33587200
diff --git a/params_shard_440.bin b/params_shard_440.bin
new file mode 100644
index 0000000000000000000000000000000000000000..755fd328c9593b338a367208b910ad03dad3c74a
--- /dev/null
+++ b/params_shard_440.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1e607dac96ddb888438f3f79583d9abaddc710e8da4420e819e39ffde9255f
+size 26869760
diff --git a/params_shard_441.bin b/params_shard_441.bin
new file mode 100644
index 0000000000000000000000000000000000000000..364425c3568018eb7e1b0a8e690f62110910e885
--- /dev/null
+++ b/params_shard_441.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582ff0bf33ba59e981b03ea02e4e4d815f7b68e7b4db0a473abd17de58a4bf9b
+size 93978624
diff --git a/params_shard_442.bin b/params_shard_442.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3a6069061aa093c2f85fdbf09464685792675976
--- /dev/null
+++ b/params_shard_442.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f7509494c90677d166f0375bd25c9786808ebf3c45ddfcbf6be5ee3ba1f8fb
+size 26894336
diff --git a/params_shard_443.bin b/params_shard_443.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a1a5c18aae2f944671ed22af6029ba5ea92ff517
--- /dev/null
+++ b/params_shard_443.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb16afafbadb77e5503fac8996d9f69801a88266303469d777f3a714690b967
+size 188088320
diff --git a/params_shard_444.bin b/params_shard_444.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e936421d3769c4c83eb1cca7299b25e944785580
--- /dev/null
+++ b/params_shard_444.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdb6180d62f313f1b361f392cf85f3b5b5e8d155db7710c50de3292477cf126
+size 23511040
diff --git a/params_shard_445.bin b/params_shard_445.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3b03d7133d62d32d44351df15a8ae3ba2b8c7ac5
--- /dev/null
+++ b/params_shard_445.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc205a16cbe18b3bdbf4f09d76188ad1f2f8f7e3d9a35605c06e0fcfc7bd5104
+size 93978624
diff --git a/params_shard_446.bin b/params_shard_446.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8d9c0fa5bb03c7d72f1022999d5f5958721cca7
--- /dev/null
+++ b/params_shard_446.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7add80582742dd5d2b8126b190bb56fc2d1db0d1c72652d67818cd863e3287a
+size 188088320
diff --git a/params_shard_447.bin b/params_shard_447.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fd26f16bbcf7cb3ef95e491c31594f31eba3aad9
--- /dev/null
+++ b/params_shard_447.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faac4ca5bb5847e5ba8f1a4d80ade3b0e5904231bd7b4428726b4aed4ad78a32
+size 23511040
diff --git a/params_shard_448.bin b/params_shard_448.bin
new file mode 100644
index 0000000000000000000000000000000000000000..db11717963959927ad95d5c7591dbff50bf33bc9
--- /dev/null
+++ b/params_shard_448.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0966e342b3f2bed947e258426d9a5aa4292333f5ad2701c87283651475f3d08
+size 33587200
diff --git a/params_shard_449.bin b/params_shard_449.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2ab66b7b80c428a85736819cee2040b91e1f84db
--- /dev/null
+++ b/params_shard_449.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6cba0858ee6df59b84796e51957f077538eb91978cf61e337731f039c08613
+size 26869760
diff --git a/params_shard_45.bin b/params_shard_45.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eafc78593fde282e7b2c6d239c342fdb5799666f
--- /dev/null
+++ b/params_shard_45.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0423b096475c1455b3aedace17adc125556a89c0f2d2e1a989d6b48891cbca90
+size 31100928
diff --git a/params_shard_450.bin b/params_shard_450.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1eacf68ec42ae9e239ed2bd5d1d28d1575eb1563
--- /dev/null
+++ b/params_shard_450.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ec630a22ba528c2b1c01025c370d6af61a8be60e57ffd5d1283ccc98103241
+size 93978624
diff --git a/params_shard_451.bin b/params_shard_451.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8b0a300385578e9339b16f874962eb701a44a9bb
--- /dev/null
+++ b/params_shard_451.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbc49dedab7ab260036dd8963a92dd3f1078ff938142968e140237871e994d8
+size 31100928
diff --git a/params_shard_452.bin b/params_shard_452.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cc5e2160232e5500f844f877b4f3f8970e66421d
--- /dev/null
+++ b/params_shard_452.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9fccb76d0781feb5e23bab6bbdbbd3eeb71b7bea90e3c69997152a5be75662
+size 33587200
diff --git a/params_shard_453.bin b/params_shard_453.bin
new file mode 100644
index 0000000000000000000000000000000000000000..14b7b76b66e7982100fab038f8089dec80d94327
--- /dev/null
+++ b/params_shard_453.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d81271094d1fcfa26234fd85eb7bd4979f85e208f1708892805ee7dbda7ed4
+size 26869760
diff --git a/params_shard_454.bin b/params_shard_454.bin
new file mode 100644
index 0000000000000000000000000000000000000000..30ae52cc80b75ceb3c3953c793fb3a443538b7ca
--- /dev/null
+++ b/params_shard_454.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b51ee2d9d540170c790ec9ab009c5d5b7f7967988e37a21aa24f0816060bd0a
+size 19304448
diff --git a/params_shard_46.bin b/params_shard_46.bin
new file mode 100644
index 0000000000000000000000000000000000000000..37d3444dd3c51dbb9ecc3116097cc1dc993ed6e2
--- /dev/null
+++ b/params_shard_46.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f0171182f884274c59740c257445de6d77958a50c32d1094c8eeb66237c49f
+size 31068160
diff --git a/params_shard_47.bin b/params_shard_47.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4b0221dd78db00484413f7766f2413368234d25b
--- /dev/null
+++ b/params_shard_47.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e6d53eacf7621aaa94021fa3c0b2a4024e1335538a41a30b2efd71cb941d89
+size 33587200
diff --git a/params_shard_48.bin b/params_shard_48.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e54b0ffac445514b9912e5a4511ea8784f64dfad
--- /dev/null
+++ b/params_shard_48.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468f6bb1208ee8baa4f5369af0d9a49447b7f79652a719bf0cd1c93930a94dae
+size 26869760
diff --git a/params_shard_49.bin b/params_shard_49.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c527ead0d06c0618c549f56442dca01fee543fe6
--- /dev/null
+++ b/params_shard_49.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d740bfc757cf8019695950cbe7df17ad7775dbce50dcc91d3fe928d3d22881b1
+size 93978624
diff --git a/params_shard_5.bin b/params_shard_5.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d3e79347fe384cbc3a9f5ace2e34a2334b1958b0
--- /dev/null
+++ b/params_shard_5.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f86bc502acd7b93b559f4abac00f4bc399327f7c47e479005f4428ffef9d1a
+size 188088320
diff --git a/params_shard_50.bin b/params_shard_50.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f906b9895f01601f4527fbccfe5635645e0b416a
--- /dev/null
+++ b/params_shard_50.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51acbb91dd96c0f60b792244f116274cbedc0cf66ff6cf4ef5b6bbb39c9fae46
+size 188088320
diff --git a/params_shard_51.bin b/params_shard_51.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4cac8b848e61aefaf8a47b72754d53856c8e3f64
--- /dev/null
+++ b/params_shard_51.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dea2cd8ead6941804cb62d42ff64124e786922f1a5fe8e404fb4fc0643ea7f1
+size 23511040
diff --git a/params_shard_52.bin b/params_shard_52.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eda64d8efb91313c25b54c2644fb5edb1002ff92
--- /dev/null
+++ b/params_shard_52.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1ae835e78878ddda2e4fc1a5a9d9caecc90469a6cbe6cdbc17b986848fe0f1
+size 93978624
diff --git a/params_shard_53.bin b/params_shard_53.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f8041c8e161baa04358fa0f810b81ab6b3a81a2c
--- /dev/null
+++ b/params_shard_53.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a08e5a10fbf663dcc7999ac32447fd97eb77a75ae94e692d119d4ad78f0d9d5
+size 22712320
diff --git a/params_shard_54.bin b/params_shard_54.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f0b30d956e407cb3f68ab0c2037bfe2ee8815679
--- /dev/null
+++ b/params_shard_54.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66a9e5b474c61403e78f3fd2b9063f5b2da47d864cb67947675e6bdf1b461ae
+size 188088320
diff --git a/params_shard_55.bin b/params_shard_55.bin
new file mode 100644
index 0000000000000000000000000000000000000000..37b7814688d4ac3fcbda7f85929a299ce46374d3
--- /dev/null
+++ b/params_shard_55.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042519da2c21440e8ed7e9085343bfd3939619ebe0a676b5977f347c71388a80
+size 23511040
diff --git a/params_shard_56.bin b/params_shard_56.bin
new file mode 100644
index 0000000000000000000000000000000000000000..77ce36a1650e511f86eadb1b74123e97085ea19a
--- /dev/null
+++ b/params_shard_56.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad1d55cc9d1c843b362f2a4055913836170dd3516b8487cce80cd518fca81e9
+size 93978624
diff --git a/params_shard_57.bin b/params_shard_57.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2c178bf98d48b6a712f448043716c1c4136edc1c
--- /dev/null
+++ b/params_shard_57.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064490b2c091dc6a200380d04dd94ee482d8e03d5f0039024e55d71ff35ec8bb
+size 188088320
diff --git a/params_shard_58.bin b/params_shard_58.bin
new file mode 100644
index 0000000000000000000000000000000000000000..72e88ccfd1adeea98924b111a8fb76b03fcf7e21
--- /dev/null
+++ b/params_shard_58.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29377ffc5dc399370ba1a4c25c3eb432b8036854b1e4425091a20dfb9abcd174
+size 23511040
diff --git a/params_shard_59.bin b/params_shard_59.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6e38984be01cd0ca7f843654f2fa895007862f29
--- /dev/null
+++ b/params_shard_59.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c39e41bd18afb96ba3aec5eea97b4fa7e2d4c17b7b52df6ea45d8389ee155f
+size 33587200
diff --git a/params_shard_6.bin b/params_shard_6.bin
new file mode 100644
index 0000000000000000000000000000000000000000..22cec395a1e0e7d0492181a09cc7d78b4dc9d648
--- /dev/null
+++ b/params_shard_6.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e153b6a08d5fb43f9b1d2b8dd843a37209ccc7562e47e15d7221f6f844093e80
+size 23511040
diff --git a/params_shard_60.bin b/params_shard_60.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0113ee79866a0d4ebda2f3a43cef7b3542cfdc00
--- /dev/null
+++ b/params_shard_60.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f34f871f4a7df5f49366412a0b0eab719d705ade1ad4aeee7e826f2fb13e65
+size 26869760
diff --git a/params_shard_61.bin b/params_shard_61.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5b5e1e2c2daf4829f479022e831684cf89200bf1
--- /dev/null
+++ b/params_shard_61.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0727c7ef7eedce5ffc5796c4a67a4c8603ef18e17e949e83d806cd219aca016e
+size 93978624
diff --git a/params_shard_62.bin b/params_shard_62.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4ae121e9e00b7523a69e53550344a1289aa34111
--- /dev/null
+++ b/params_shard_62.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d150fec88033a960b5c654658452e68a99946849a4d440f63a6decee3d97d247
+size 31100928
diff --git a/params_shard_63.bin b/params_shard_63.bin
new file mode 100644
index 0000000000000000000000000000000000000000..62a82d751023c5a5703d570405adb08d049286bf
--- /dev/null
+++ b/params_shard_63.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a57bfd51cb141ca05f6cca22259becf20262f4f525ddbedaac4fd9ca10f0f6
+size 188088320
diff --git a/params_shard_64.bin b/params_shard_64.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7011cf4f47c7d1e4b7641b51310d550be6e6a860
--- /dev/null
+++ b/params_shard_64.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd364988c4b2f7d266481369864a7c959576d9e01662a6ff2c2b0b160c1d628
+size 23511040
diff --git a/params_shard_65.bin b/params_shard_65.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e7ee3fb698091f897004154917814b3ddf84580b
--- /dev/null
+++ b/params_shard_65.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee88910c550d0146a921f7c0d019b3ebee90b90ad29af0b66562c50d810007da
+size 33587200
diff --git a/params_shard_66.bin b/params_shard_66.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d0a7056adb3af807e7058f44f3af7afc8cc0a935
--- /dev/null
+++ b/params_shard_66.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed71bcf2872f320ca9e744dabb5d83f6898067a0ffac78d69ac7271fc00447d5
+size 26869760
diff --git a/params_shard_67.bin b/params_shard_67.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b94450ba39dc74669576ccf56bc9efd87a3a0ec6
--- /dev/null
+++ b/params_shard_67.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f40d54a6628d58290f4eebeac7c021eaf933769ee4de71f62d91b1653b9aa50
+size 93978624
diff --git a/params_shard_68.bin b/params_shard_68.bin
new file mode 100644
index 0000000000000000000000000000000000000000..389a185341be832daf6a09349a8f521e055dc685
--- /dev/null
+++ b/params_shard_68.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046791cfac0ffff70863b13aa2a8a04d4e09257068b27de429209592094a90b4
+size 188088320
diff --git a/params_shard_69.bin b/params_shard_69.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6b260446f105bda9aa8dda73e216357c46c4e55b
--- /dev/null
+++ b/params_shard_69.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923b6bd465357011aea60209dc19f46e095897482922a652cef7c44a5173d251
+size 23511040
diff --git a/params_shard_7.bin b/params_shard_7.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ff6ef673fd1a6ae52d7c82304caf8fe32d92b19
--- /dev/null
+++ b/params_shard_7.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abae893a6e5f0c2f585030ef52e673bf324c291032e8e98b9742654ca07548e2
+size 33587200
diff --git a/params_shard_70.bin b/params_shard_70.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dd0945a1470b669fb4cadfd2bf1773e67b4c476e
--- /dev/null
+++ b/params_shard_70.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b275ec17ef98ed91a5887a87bf0958a70ad5573092b9ce1320e4b6405feb09
+size 33587200
diff --git a/params_shard_71.bin b/params_shard_71.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1aef68190dab935407cfecd289b9318a47dc1127
--- /dev/null
+++ b/params_shard_71.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6e04fb175cb3b6c5cd1a33175b631617101bb425e0068e29958f58d014a262
+size 31117312
diff --git a/params_shard_72.bin b/params_shard_72.bin
new file mode 100644
index 0000000000000000000000000000000000000000..81217b56e02a2cf172216f40c8d582581032cf4a
--- /dev/null
+++ b/params_shard_72.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7206ca8e8ce23cbb4fe96982572060a9da48602ffecd858b44857bf9f0f6ca60
+size 31068160
diff --git a/params_shard_73.bin b/params_shard_73.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6c4c3833b9cd2fdc6b35f0d1da78f462b97208e
--- /dev/null
+++ b/params_shard_73.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac40cb5230a840f74fb14c267ea34a2e9fc08ebb9563fd9591accbeffb11eaf
+size 93978624
diff --git a/params_shard_74.bin b/params_shard_74.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ebb57839140807680bbbcf7da45e22d4b74e212a
--- /dev/null
+++ b/params_shard_74.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cefc55984f938453abea95c980aba43e3d8724bc8323a60a7ff08130140cbc
+size 188088320
diff --git a/params_shard_75.bin b/params_shard_75.bin
new file mode 100644
index 0000000000000000000000000000000000000000..58ee075c48257eb139369603133da1089fd51bee
--- /dev/null
+++ b/params_shard_75.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88695c5fec2c90da8e1d46c1c477916d032ab928c9539dae6880b037042be18e
+size 23511040
diff --git a/params_shard_76.bin b/params_shard_76.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c2f2566a93b06e07fdaad89273982d7180778e95
--- /dev/null
+++ b/params_shard_76.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee0ed8b0eede14b72af15ab66679b3d09dc193130f1b64f61350678213149a0
+size 33587200
diff --git a/params_shard_77.bin b/params_shard_77.bin
new file mode 100644
index 0000000000000000000000000000000000000000..20d3b17317f342ae4033989148f4eb132ff0f4d6
--- /dev/null
+++ b/params_shard_77.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eeb2157f06b5ef3df7c28437e51744741cbe8456119b9af1eab0d5fffa348eb
+size 26869760
diff --git a/params_shard_78.bin b/params_shard_78.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6081f3fe5f4e4dbebe8dcb29f577272ec9e578f4
--- /dev/null
+++ b/params_shard_78.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e51da8914ecb40cf4214881d783e6848aa448c488089feb9c63e480bd61820
+size 188088320
diff --git a/params_shard_79.bin b/params_shard_79.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ee94a7a04cb39b06912a2738e9c49aba1de2245
--- /dev/null
+++ b/params_shard_79.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b65f65653fa8bd5befaac14595f1000accb923ae756e6b1f5f9c6570c9946f9
+size 23511040
diff --git a/params_shard_8.bin b/params_shard_8.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7fb2f11fb10b0012fa6cc06f089cf8de55d349ed
--- /dev/null
+++ b/params_shard_8.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a56eab0ac2866e6ea2afbfe6b3af713448f336a58e99661546b9a3a822110ef
+size 26869760
diff --git a/params_shard_80.bin b/params_shard_80.bin
new file mode 100644
index 0000000000000000000000000000000000000000..37d98a612835c5fecbb9cd5e42b1d3183deb19ee
--- /dev/null
+++ b/params_shard_80.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff4153e46504ec45dc2d7c052073294b5f14a0eba01c8838a6c908887dcad11
+size 33587200
diff --git a/params_shard_81.bin b/params_shard_81.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0d6ca79c948b130f5100954775b5414e28bfdd6d
--- /dev/null
+++ b/params_shard_81.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee460e3c57513bfc4f39bf23d8558937fe3b0f00148ad1a52f58da737975232
+size 26869760
diff --git a/params_shard_82.bin b/params_shard_82.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4ff5cf8aebfef5f070c84ee21f5f69a18d91d99d
--- /dev/null
+++ b/params_shard_82.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acda215c4533a1fa64e6750fe20dc2b88fb3c22b0ee9c96e305ac653d1c27ac
+size 93978624
diff --git a/params_shard_83.bin b/params_shard_83.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5d3e75eb0cb270881d3ff685abfb8ffeb2f9aa7a
--- /dev/null
+++ b/params_shard_83.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58ae68d4d438ce9a8df85426b092e1d6c283e47ba0ac713ef9c71dc9b8691d0
+size 30269440
diff --git a/params_shard_84.bin b/params_shard_84.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fb4bc3a1b912cd97e59cb65425615d3d26ea9b16
--- /dev/null
+++ b/params_shard_84.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ddcad5c0bfdb25370816ce6fbe4b40e66572047bc75fdef2a1d7d34971e02f
+size 93978624
diff --git a/params_shard_85.bin b/params_shard_85.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8c0b9cc79f516f3f69931d852940be3aa142cd18
--- /dev/null
+++ b/params_shard_85.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b186f1724787b7bd88a343b2d847399e72d5298c6f60b2848b30e648878ddc88
+size 188088320
diff --git a/params_shard_86.bin b/params_shard_86.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b7e47acc1d0dbf3b3171524f543a7a5072cfd504
--- /dev/null
+++ b/params_shard_86.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0cb276f47f81e7e87e59f454377568c590d1a2ae98a6472405f9d13f7f572c
+size 23511040
diff --git a/params_shard_87.bin b/params_shard_87.bin
new file mode 100644
index 0000000000000000000000000000000000000000..edd3054aa713ddbb698b1b2fecf0d795dea74589
--- /dev/null
+++ b/params_shard_87.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae966b914ffc63d0b5f07d2865ac40be82cb361e314ec2d0959992c542c1a1a2
+size 33587200
diff --git a/params_shard_88.bin b/params_shard_88.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ad4847297c8a237868a3caa9b8749dd94b4c9c48
--- /dev/null
+++ b/params_shard_88.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac593d8104b4ec872f46c411b9d0425ef725f053a897fdf6094f28a6235fb632
+size 26869760
diff --git a/params_shard_89.bin b/params_shard_89.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a90646813548ef29dc5bfbc425d1ade1c82a6ed
--- /dev/null
+++ b/params_shard_89.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975563824935923e1fce6579c410456ac59c51148b43bb3bcccd4db7a2e2b3a7
+size 93978624
diff --git a/params_shard_9.bin b/params_shard_9.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8109fb9939f47ef5b2848a30b3e5be548e1325be
--- /dev/null
+++ b/params_shard_9.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd278174daed0b46f937d4f86a85a136123b63469c04a4c1943259cdd2beee5
+size 420679680
diff --git a/params_shard_90.bin b/params_shard_90.bin
new file mode 100644
index 0000000000000000000000000000000000000000..368107b3cff93073c9ab690e5171d2626a325ef4
--- /dev/null
+++ b/params_shard_90.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d5f9d84c3a7c27f156ede2085572cae7ca9b0d9b167701117b779509750cd5
+size 31117312
diff --git a/params_shard_91.bin b/params_shard_91.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c2ad2097907d6c0d5ff9764e77944c636e50ebe0
--- /dev/null
+++ b/params_shard_91.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7032e7ae454e3eaf6f6d9b379119b1201b6d49f37c73436013e6ae74f3bfe5b
+size 188088320
diff --git a/params_shard_92.bin b/params_shard_92.bin
new file mode 100644
index 0000000000000000000000000000000000000000..17a288e7c91e4d2e255295de980ffc3d9d6576c1
--- /dev/null
+++ b/params_shard_92.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c56a75491ec1a34b068920a58ee6c1f5ffee563870289056de87a5874f6632
+size 23511040
diff --git a/params_shard_93.bin b/params_shard_93.bin
new file mode 100644
index 0000000000000000000000000000000000000000..276543ceaaee8caf16e6c6fef083db1a5a251fd2
--- /dev/null
+++ b/params_shard_93.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09094b0897ee8ef2beb4bb0ec6c9c1cff472dacf1a81b99d5103101fb8ff8d8
+size 33587200
diff --git a/params_shard_94.bin b/params_shard_94.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3b7465ca7e6cfafbba86da7b79b2b4d27f8f8d44
--- /dev/null
+++ b/params_shard_94.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e4fe855b5de5892b5f20dc48087ab7816bd8ae1dd388a16c46517c4a888afc
+size 26869760
diff --git a/params_shard_95.bin b/params_shard_95.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fee42234396897b9961a4c2ce597b4ebaa53ae43
--- /dev/null
+++ b/params_shard_95.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cabf8992f7d43658c9c497d808d482d549901eeb2b733dfeb42c587d90a3d4
+size 33587200
diff --git a/params_shard_96.bin b/params_shard_96.bin
new file mode 100644
index 0000000000000000000000000000000000000000..87529bd08d90a058acd2d997a5bef9e115a1fa7f
--- /dev/null
+++ b/params_shard_96.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fe7e780b63b4cda7bfde3121395ff82b5d3552ac8860608d10cddb19978168
+size 26869760
diff --git a/params_shard_97.bin b/params_shard_97.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3333d43b664798e33115988e86b620ae91410a91
--- /dev/null
+++ b/params_shard_97.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e48ab02f1684a06051444d2f76b0be73c84761efc253f584517ddfd0f87c41
+size 93978624
diff --git a/params_shard_98.bin b/params_shard_98.bin
new file mode 100644
index 0000000000000000000000000000000000000000..817828be285a661e7cf8b59055dd6dbc30132508
--- /dev/null
+++ b/params_shard_98.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd7c8608c4b3dee9b99f3614740ff5e3957c1955138fde8eb361f107e87aa87
+size 26894336
diff --git a/params_shard_99.bin b/params_shard_99.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9c75d199c9d764d3e5054084e5232766374bd9df
--- /dev/null
+++ b/params_shard_99.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b782c7a6ba95dcab75ba3005bd3b7c7c5ca8d9875059d383ee15c4fb1659779d
+size 188088320
diff --git a/private-llm-config.json b/private-llm-config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b57966f0650eb4710137dc60653b0e58428e647b
--- /dev/null
+++ b/private-llm-config.json
@@ -0,0 +1,51 @@
+{
+  "model_type": "llama",
+  "quantization": "w3a16g40sym",
+  "model_config": {
+    "hidden_size": 8192,
+    "intermediate_size": 28672,
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "rms_norm_eps": 1e-05,
+    "vocab_size": 128256,
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "context_window_size": 4096,
+    "prefill_chunk_size": 128,
+    "num_key_value_heads": 8,
+    "head_dim": 128,
+    "tensor_parallel_shards": 1,
+    "pipeline_parallel_stages": 1,
+    "max_batch_size": 80
+  },
+  "vocab_size": 128256,
+  "context_window_size": 4096,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 128,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "mean_gen_len": 128,
+  "max_gen_len": 512,
+  "shift_fill_factor": 0.3,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.0,
+  "top_p": 0.95,
+  "conv_template": "llama-3",
+  "pad_token_id": 0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "tokenizer_files": [
+    "tokenizer.json",
+    "tokenizer_config.json"
+  ],
+  "version": "0.1.0"
+}
\ No newline at end of file
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c91fde4f2240d14fb005a6ab3a9e6fd9245d069e
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}