Upload folder using huggingface_hub

.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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3ForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfbdfdb2da57639147314d8f1e669666db9d3ebfe8ed5dd6af8657492047906f
+size 4537714712

model-00002-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8944e6bae2d7b6b12b91cd97d4b9b9a7e37ac969fabfceee4d9ebed7037c496
+size 4802607584

model-00003-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d660198168ee73ea1fc63129aee2106fca881b23df40b4026ac4675a594d644c
+size 4949365440

model-00004-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c6a9be3ab3913e5d87fc42a95d4eafd5a7749e578ee6fbf3eb2bfb690159a1
+size 4802607584

model-00005-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8e78da99d4cd3f7aadef8b84d0b4f0941a4b3c0be41efc587dbdd2a8c57c2e
+size 4949365464

model-00006-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0dd8aa1d717ee46a59ab573ab194db99350bfef78c5abf24c5e12e6eb3dbfd
+size 4802607616

model-00007-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc92c26cd9ed86a2846c36d9368e2e70a0c11958bb604af1e9fa950389ea7e8
+size 4949365464

model-00008-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad3747c2dc4c46016912cc8100917f494283cef20e340317fe8ddbc0fc13426
+size 4802607616

model-00009-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc79fb847d19fc21de45ed613770f94deac9b6d9bec81aa95e0bd9d2163053a
+size 4949365464

model-00010-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726076d63fe58da049f11eb709a11016d4e1284893360c09e3651e68d889cb1f
+size 4802607616

model-00011-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d32a9ec8394b2193038b4e60b75b2d58ee3633536f248169784edb590ecfea5
+size 4949365464

model-00012-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0125efaf23437f0e0567cb0a6a9fae386fb80e635864cc0ac0c76d39c143a8d
+size 4802607616

model-00013-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c570f240deb3936d275a31074d077980195c38452d6f6ce1b11b9ec64fb320e
+size 4949365464

model-00014-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c37ed8894a6005a3f3f4c3030d12934ca28440e9fb085a47ad56915cbfbb3e
+size 4802607616

model-00015-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389dfe7e664b47fbe641670e612fdb266304e689d21baafde2526df0bd07518e
+size 4949365464

model-00016-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41921748ba8b2d6cc752166338100068cb60487a2fce9f18cc48f088480f46c0
+size 4802607616

model-00017-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c427ae7a6430c788229d225347979e2809e24f4f53675c2df78427ee8d230fb3
+size 4949365464

model-00018-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc432c10d18dca1e1937269cfa040991e5d374995ce5b9d5b1b22e755502980
+size 4802607616

model-00019-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9c1a614fd65b8e4fe5e5484e29999fe135e4e7dbe5f9e6e181fe883c79159f
+size 4949365464

model-00020-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665da6809358daf3c405980392104ff2284a81b8f0bc333828e82b521da5349c
+size 4802607616

model-00021-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2600c3d44fc4d7d8f5f30bed46dd184c840e211190d27314cc8d76b99dd370a8
+size 4949365464

model-00022-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34a51a3c3a7ec89713ee137bd5b007464e1bac2db42d37d3f5f530b813a3f2c
+size 4802607616

model-00023-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63adee79cb1ca78486f57622201710230a9d1b97e6f17273bb259db661585346
+size 4949365464

model-00024-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb3737d5c176de00195dfb22ad22f349e9fca00c60efda3740c8d0e06e4cc77
+size 4802607616

model-00025-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e86f5fa0609a2abec68c81d252daa732475cef8d9723745caab0dd06cff935d
+size 4949365464

model-00026-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6f36fafdc3d1688ef758fad63c88b7c41dfc4b3b6f858aa6d1720cb65d80b1
+size 4802607616

model-00027-of-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65494d7be7e9f2cd0e4a7436ad5754a278b418f7c5343519bc8d5dfbfa291b65
+size 1572946696

model.safetensors.index.json

@@ -0,0 +1,714 @@
+{
+  "metadata": {
+    "total_size": 127936864256
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00027.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00027.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00027.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00027.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00027.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00027.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00027.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00027.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00027.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00027.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00027.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00027.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00027.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00027.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00027.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00027.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00020-of-00027.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00027.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00021-of-00027.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00022-of-00027.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00023-of-00027.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00024-of-00027.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00025-of-00027.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00027-of-00027.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00026-of-00027.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00027.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00027.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00027.safetensors",
+    "model.norm.weight": "model-00027-of-00027.safetensors",
+    "score.weight": "model-00027-of-00027.safetensors"
+  }
+}

reward_bench_results.out

@@ -0,0 +1,408 @@
+2025-05-21 11:35:59 - INFO - rewardbench.rewardbench - Running reward model on /home/hshin/outputs/rm_22_qwen_inst/rmtr_nrt_n8_Qwen3-32B_hs3_scale_only_trl_with_margin_filtered_0.0003_0_1_lora_r4_lora_alpha24_lora_dropout0/checkpoint-100/merged with chat template None
+2025-05-21 11:35:59 - INFO - rewardbench.rewardbench - Using reward model config: {'model_builder': <bound method _BaseAutoModelClass.from_pretrained of <class 'transformers.models.auto.modeling_auto.AutoModelForSequenceClassification'>>, 'pipeline_builder': <class 'rewardbench.models.pipeline.RewardBenchPipeline'>, 'quantized': True, 'custom_dialogue': False, 'model_type': 'Seq. Classifier'}
+2025-05-21 11:35:59 - INFO - rewardbench.rewardbench - *** Load dataset ***
+2025-05-21 11:35:59 - INFO - rewardbench.rewardbench - Running core eval dataset.
+2025-05-21 11:36:07 - INFO - rewardbench.rewardbench - *** Preparing dataset with HF Transformers ***
+2025-05-21 11:36:08 - INFO - rewardbench.rewardbench - *** Load reward model ***
+2025-05-21 11:37:40 - INFO - rewardbench.rewardbench - RM inference step 0/374
+2025-05-21 11:37:44 - INFO - rewardbench.rewardbench - RM inference step 1/374
+2025-05-21 11:37:45 - INFO - rewardbench.rewardbench - RM inference step 2/374
+2025-05-21 11:37:48 - INFO - rewardbench.rewardbench - RM inference step 3/374
+2025-05-21 11:37:49 - INFO - rewardbench.rewardbench - RM inference step 4/374
+2025-05-21 11:37:53 - INFO - rewardbench.rewardbench - RM inference step 5/374
+2025-05-21 11:37:55 - INFO - rewardbench.rewardbench - RM inference step 6/374
+2025-05-21 11:37:57 - INFO - rewardbench.rewardbench - RM inference step 7/374
+2025-05-21 11:37:59 - INFO - rewardbench.rewardbench - RM inference step 8/374
+2025-05-21 11:38:01 - INFO - rewardbench.rewardbench - RM inference step 9/374
+2025-05-21 11:38:03 - INFO - rewardbench.rewardbench - RM inference step 10/374
+2025-05-21 11:38:04 - INFO - rewardbench.rewardbench - RM inference step 11/374
+2025-05-21 11:38:06 - INFO - rewardbench.rewardbench - RM inference step 12/374
+2025-05-21 11:38:08 - INFO - rewardbench.rewardbench - RM inference step 13/374
+2025-05-21 11:38:10 - INFO - rewardbench.rewardbench - RM inference step 14/374
+2025-05-21 11:38:12 - INFO - rewardbench.rewardbench - RM inference step 15/374
+2025-05-21 11:38:13 - INFO - rewardbench.rewardbench - RM inference step 16/374
+2025-05-21 11:38:16 - INFO - rewardbench.rewardbench - RM inference step 17/374
+2025-05-21 11:38:17 - INFO - rewardbench.rewardbench - RM inference step 18/374
+2025-05-21 11:38:19 - INFO - rewardbench.rewardbench - RM inference step 19/374
+2025-05-21 11:38:21 - INFO - rewardbench.rewardbench - RM inference step 20/374
+2025-05-21 11:38:23 - INFO - rewardbench.rewardbench - RM inference step 21/374
+2025-05-21 11:38:24 - INFO - rewardbench.rewardbench - RM inference step 22/374
+2025-05-21 11:38:25 - INFO - rewardbench.rewardbench - RM inference step 23/374
+2025-05-21 11:38:26 - INFO - rewardbench.rewardbench - RM inference step 24/374
+2025-05-21 11:38:29 - INFO - rewardbench.rewardbench - RM inference step 25/374
+2025-05-21 11:38:31 - INFO - rewardbench.rewardbench - RM inference step 26/374
+2025-05-21 11:38:36 - INFO - rewardbench.rewardbench - RM inference step 27/374
+2025-05-21 11:38:40 - INFO - rewardbench.rewardbench - RM inference step 28/374
+2025-05-21 11:38:43 - INFO - rewardbench.rewardbench - RM inference step 29/374
+2025-05-21 11:38:48 - INFO - rewardbench.rewardbench - RM inference step 30/374
+2025-05-21 11:38:52 - INFO - rewardbench.rewardbench - RM inference step 31/374
+2025-05-21 11:38:56 - INFO - rewardbench.rewardbench - RM inference step 32/374
+2025-05-21 11:39:01 - INFO - rewardbench.rewardbench - RM inference step 33/374
+2025-05-21 11:39:05 - INFO - rewardbench.rewardbench - RM inference step 34/374
+2025-05-21 11:39:06 - INFO - rewardbench.rewardbench - RM inference step 35/374
+2025-05-21 11:39:10 - INFO - rewardbench.rewardbench - RM inference step 36/374
+2025-05-21 11:39:12 - INFO - rewardbench.rewardbench - RM inference step 37/374
+2025-05-21 11:39:15 - INFO - rewardbench.rewardbench - RM inference step 38/374
+2025-05-21 11:39:18 - INFO - rewardbench.rewardbench - RM inference step 39/374
+2025-05-21 11:39:21 - INFO - rewardbench.rewardbench - RM inference step 40/374
+2025-05-21 11:39:23 - INFO - rewardbench.rewardbench - RM inference step 41/374
+2025-05-21 11:39:26 - INFO - rewardbench.rewardbench - RM inference step 42/374
+2025-05-21 11:39:27 - INFO - rewardbench.rewardbench - RM inference step 43/374
+2025-05-21 11:39:30 - INFO - rewardbench.rewardbench - RM inference step 44/374
+2025-05-21 11:39:32 - INFO - rewardbench.rewardbench - RM inference step 45/374
+2025-05-21 11:39:34 - INFO - rewardbench.rewardbench - RM inference step 46/374
+2025-05-21 11:39:36 - INFO - rewardbench.rewardbench - RM inference step 47/374
+2025-05-21 11:39:37 - INFO - rewardbench.rewardbench - RM inference step 48/374
+2025-05-21 11:39:39 - INFO - rewardbench.rewardbench - RM inference step 49/374
+2025-05-21 11:39:40 - INFO - rewardbench.rewardbench - RM inference step 50/374
+2025-05-21 11:39:42 - INFO - rewardbench.rewardbench - RM inference step 51/374
+2025-05-21 11:39:43 - INFO - rewardbench.rewardbench - RM inference step 52/374
+2025-05-21 11:39:45 - INFO - rewardbench.rewardbench - RM inference step 53/374
+2025-05-21 11:39:45 - INFO - rewardbench.rewardbench - RM inference step 54/374
+2025-05-21 11:39:46 - INFO - rewardbench.rewardbench - RM inference step 55/374
+2025-05-21 11:39:47 - INFO - rewardbench.rewardbench - RM inference step 56/374
+2025-05-21 11:39:50 - INFO - rewardbench.rewardbench - RM inference step 57/374
+2025-05-21 11:39:50 - INFO - rewardbench.rewardbench - RM inference step 58/374
+2025-05-21 11:39:51 - INFO - rewardbench.rewardbench - RM inference step 59/374
+2025-05-21 11:39:52 - INFO - rewardbench.rewardbench - RM inference step 60/374
+2025-05-21 11:39:53 - INFO - rewardbench.rewardbench - RM inference step 61/374
+2025-05-21 11:39:54 - INFO - rewardbench.rewardbench - RM inference step 62/374
+2025-05-21 11:39:54 - INFO - rewardbench.rewardbench - RM inference step 63/374
+2025-05-21 11:39:55 - INFO - rewardbench.rewardbench - RM inference step 64/374
+2025-05-21 11:39:56 - INFO - rewardbench.rewardbench - RM inference step 65/374
+2025-05-21 11:39:57 - INFO - rewardbench.rewardbench - RM inference step 66/374
+2025-05-21 11:39:58 - INFO - rewardbench.rewardbench - RM inference step 67/374
+2025-05-21 11:39:58 - INFO - rewardbench.rewardbench - RM inference step 68/374
+2025-05-21 11:39:59 - INFO - rewardbench.rewardbench - RM inference step 69/374
+2025-05-21 11:39:59 - INFO - rewardbench.rewardbench - RM inference step 70/374
+2025-05-21 11:40:00 - INFO - rewardbench.rewardbench - RM inference step 71/374
+2025-05-21 11:40:01 - INFO - rewardbench.rewardbench - RM inference step 72/374
+2025-05-21 11:40:02 - INFO - rewardbench.rewardbench - RM inference step 73/374
+2025-05-21 11:40:03 - INFO - rewardbench.rewardbench - RM inference step 74/374
+2025-05-21 11:40:04 - INFO - rewardbench.rewardbench - RM inference step 75/374
+2025-05-21 11:40:06 - INFO - rewardbench.rewardbench - RM inference step 76/374
+2025-05-21 11:40:08 - INFO - rewardbench.rewardbench - RM inference step 77/374
+2025-05-21 11:40:09 - INFO - rewardbench.rewardbench - RM inference step 78/374
+2025-05-21 11:40:11 - INFO - rewardbench.rewardbench - RM inference step 79/374
+2025-05-21 11:40:12 - INFO - rewardbench.rewardbench - RM inference step 80/374
+2025-05-21 11:40:14 - INFO - rewardbench.rewardbench - RM inference step 81/374
+2025-05-21 11:40:15 - INFO - rewardbench.rewardbench - RM inference step 82/374
+2025-05-21 11:40:17 - INFO - rewardbench.rewardbench - RM inference step 83/374
+2025-05-21 11:40:18 - INFO - rewardbench.rewardbench - RM inference step 84/374
+2025-05-21 11:40:20 - INFO - rewardbench.rewardbench - RM inference step 85/374
+2025-05-21 11:40:22 - INFO - rewardbench.rewardbench - RM inference step 86/374
+2025-05-21 11:40:24 - INFO - rewardbench.rewardbench - RM inference step 87/374
+2025-05-21 11:40:26 - INFO - rewardbench.rewardbench - RM inference step 88/374
+2025-05-21 11:40:28 - INFO - rewardbench.rewardbench - RM inference step 89/374
+2025-05-21 11:40:29 - INFO - rewardbench.rewardbench - RM inference step 90/374
+2025-05-21 11:40:30 - INFO - rewardbench.rewardbench - RM inference step 91/374
+2025-05-21 11:40:31 - INFO - rewardbench.rewardbench - RM inference step 92/374
+2025-05-21 11:40:31 - INFO - rewardbench.rewardbench - RM inference step 93/374
+2025-05-21 11:40:32 - INFO - rewardbench.rewardbench - RM inference step 94/374
+2025-05-21 11:40:34 - INFO - rewardbench.rewardbench - RM inference step 95/374
+2025-05-21 11:40:35 - INFO - rewardbench.rewardbench - RM inference step 96/374
+2025-05-21 11:40:36 - INFO - rewardbench.rewardbench - RM inference step 97/374
+2025-05-21 11:40:38 - INFO - rewardbench.rewardbench - RM inference step 98/374
+2025-05-21 11:40:39 - INFO - rewardbench.rewardbench - RM inference step 99/374
+2025-05-21 11:40:41 - INFO - rewardbench.rewardbench - RM inference step 100/374
+2025-05-21 11:40:42 - INFO - rewardbench.rewardbench - RM inference step 101/374
+2025-05-21 11:40:44 - INFO - rewardbench.rewardbench - RM inference step 102/374
+2025-05-21 11:40:45 - INFO - rewardbench.rewardbench - RM inference step 103/374
+2025-05-21 11:40:47 - INFO - rewardbench.rewardbench - RM inference step 104/374
+2025-05-21 11:40:48 - INFO - rewardbench.rewardbench - RM inference step 105/374
+2025-05-21 11:40:49 - INFO - rewardbench.rewardbench - RM inference step 106/374
+2025-05-21 11:40:51 - INFO - rewardbench.rewardbench - RM inference step 107/374
+2025-05-21 11:40:52 - INFO - rewardbench.rewardbench - RM inference step 108/374
+2025-05-21 11:40:54 - INFO - rewardbench.rewardbench - RM inference step 109/374
+2025-05-21 11:40:55 - INFO - rewardbench.rewardbench - RM inference step 110/374
+2025-05-21 11:40:56 - INFO - rewardbench.rewardbench - RM inference step 111/374
+2025-05-21 11:40:58 - INFO - rewardbench.rewardbench - RM inference step 112/374
+2025-05-21 11:40:59 - INFO - rewardbench.rewardbench - RM inference step 113/374
+2025-05-21 11:41:01 - INFO - rewardbench.rewardbench - RM inference step 114/374
+2025-05-21 11:41:03 - INFO - rewardbench.rewardbench - RM inference step 115/374
+2025-05-21 11:41:04 - INFO - rewardbench.rewardbench - RM inference step 116/374
+2025-05-21 11:41:05 - INFO - rewardbench.rewardbench - RM inference step 117/374
+2025-05-21 11:41:06 - INFO - rewardbench.rewardbench - RM inference step 118/374
+2025-05-21 11:41:08 - INFO - rewardbench.rewardbench - RM inference step 119/374
+2025-05-21 11:41:09 - INFO - rewardbench.rewardbench - RM inference step 120/374
+2025-05-21 11:41:11 - INFO - rewardbench.rewardbench - RM inference step 121/374
+2025-05-21 11:41:13 - INFO - rewardbench.rewardbench - RM inference step 122/374
+2025-05-21 11:41:13 - INFO - rewardbench.rewardbench - RM inference step 123/374
+2025-05-21 11:41:15 - INFO - rewardbench.rewardbench - RM inference step 124/374
+2025-05-21 11:41:18 - INFO - rewardbench.rewardbench - RM inference step 125/374
+2025-05-21 11:41:19 - INFO - rewardbench.rewardbench - RM inference step 126/374
+2025-05-21 11:41:20 - INFO - rewardbench.rewardbench - RM inference step 127/374
+2025-05-21 11:41:21 - INFO - rewardbench.rewardbench - RM inference step 128/374
+2025-05-21 11:41:22 - INFO - rewardbench.rewardbench - RM inference step 129/374
+2025-05-21 11:41:23 - INFO - rewardbench.rewardbench - RM inference step 130/374
+2025-05-21 11:41:25 - INFO - rewardbench.rewardbench - RM inference step 131/374
+2025-05-21 11:41:26 - INFO - rewardbench.rewardbench - RM inference step 132/374
+2025-05-21 11:41:27 - INFO - rewardbench.rewardbench - RM inference step 133/374
+2025-05-21 11:41:28 - INFO - rewardbench.rewardbench - RM inference step 134/374
+2025-05-21 11:41:29 - INFO - rewardbench.rewardbench - RM inference step 135/374
+2025-05-21 11:41:30 - INFO - rewardbench.rewardbench - RM inference step 136/374
+2025-05-21 11:41:31 - INFO - rewardbench.rewardbench - RM inference step 137/374
+2025-05-21 11:41:32 - INFO - rewardbench.rewardbench - RM inference step 138/374
+2025-05-21 11:41:33 - INFO - rewardbench.rewardbench - RM inference step 139/374
+2025-05-21 11:41:34 - INFO - rewardbench.rewardbench - RM inference step 140/374
+2025-05-21 11:41:35 - INFO - rewardbench.rewardbench - RM inference step 141/374
+2025-05-21 11:41:36 - INFO - rewardbench.rewardbench - RM inference step 142/374
+2025-05-21 11:41:37 - INFO - rewardbench.rewardbench - RM inference step 143/374
+2025-05-21 11:41:38 - INFO - rewardbench.rewardbench - RM inference step 144/374
+2025-05-21 11:41:39 - INFO - rewardbench.rewardbench - RM inference step 145/374
+2025-05-21 11:41:40 - INFO - rewardbench.rewardbench - RM inference step 146/374
+2025-05-21 11:41:42 - INFO - rewardbench.rewardbench - RM inference step 147/374
+2025-05-21 11:41:43 - INFO - rewardbench.rewardbench - RM inference step 148/374
+2025-05-21 11:41:44 - INFO - rewardbench.rewardbench - RM inference step 149/374
+2025-05-21 11:41:45 - INFO - rewardbench.rewardbench - RM inference step 150/374
+2025-05-21 11:41:46 - INFO - rewardbench.rewardbench - RM inference step 151/374
+2025-05-21 11:41:47 - INFO - rewardbench.rewardbench - RM inference step 152/374
+2025-05-21 11:41:48 - INFO - rewardbench.rewardbench - RM inference step 153/374
+2025-05-21 11:41:49 - INFO - rewardbench.rewardbench - RM inference step 154/374
+2025-05-21 11:41:50 - INFO - rewardbench.rewardbench - RM inference step 155/374
+2025-05-21 11:41:51 - INFO - rewardbench.rewardbench - RM inference step 156/374
+2025-05-21 11:41:52 - INFO - rewardbench.rewardbench - RM inference step 157/374
+2025-05-21 11:41:53 - INFO - rewardbench.rewardbench - RM inference step 158/374
+2025-05-21 11:41:53 - INFO - rewardbench.rewardbench - RM inference step 159/374
+2025-05-21 11:41:54 - INFO - rewardbench.rewardbench - RM inference step 160/374
+2025-05-21 11:41:55 - INFO - rewardbench.rewardbench - RM inference step 161/374
+2025-05-21 11:41:56 - INFO - rewardbench.rewardbench - RM inference step 162/374
+2025-05-21 11:41:57 - INFO - rewardbench.rewardbench - RM inference step 163/374
+2025-05-21 11:41:58 - INFO - rewardbench.rewardbench - RM inference step 164/374
+2025-05-21 11:41:59 - INFO - rewardbench.rewardbench - RM inference step 165/374
+2025-05-21 11:42:00 - INFO - rewardbench.rewardbench - RM inference step 166/374
+2025-05-21 11:42:01 - INFO - rewardbench.rewardbench - RM inference step 167/374
+2025-05-21 11:42:02 - INFO - rewardbench.rewardbench - RM inference step 168/374
+2025-05-21 11:42:02 - INFO - rewardbench.rewardbench - RM inference step 169/374
+2025-05-21 11:42:03 - INFO - rewardbench.rewardbench - RM inference step 170/374
+2025-05-21 11:42:04 - INFO - rewardbench.rewardbench - RM inference step 171/374
+2025-05-21 11:42:05 - INFO - rewardbench.rewardbench - RM inference step 172/374
+2025-05-21 11:42:05 - INFO - rewardbench.rewardbench - RM inference step 173/374
+2025-05-21 11:42:06 - INFO - rewardbench.rewardbench - RM inference step 174/374
+2025-05-21 11:42:07 - INFO - rewardbench.rewardbench - RM inference step 175/374
+2025-05-21 11:42:07 - INFO - rewardbench.rewardbench - RM inference step 176/374
+2025-05-21 11:42:08 - INFO - rewardbench.rewardbench - RM inference step 177/374
+2025-05-21 11:42:09 - INFO - rewardbench.rewardbench - RM inference step 178/374
+2025-05-21 11:42:11 - INFO - rewardbench.rewardbench - RM inference step 179/374
+2025-05-21 11:42:12 - INFO - rewardbench.rewardbench - RM inference step 180/374
+2025-05-21 11:42:13 - INFO - rewardbench.rewardbench - RM inference step 181/374
+2025-05-21 11:42:14 - INFO - rewardbench.rewardbench - RM inference step 182/374
+2025-05-21 11:42:15 - INFO - rewardbench.rewardbench - RM inference step 183/374
+2025-05-21 11:42:17 - INFO - rewardbench.rewardbench - RM inference step 184/374
+2025-05-21 11:42:18 - INFO - rewardbench.rewardbench - RM inference step 185/374
+2025-05-21 11:42:20 - INFO - rewardbench.rewardbench - RM inference step 186/374
+2025-05-21 11:42:21 - INFO - rewardbench.rewardbench - RM inference step 187/374
+2025-05-21 11:42:22 - INFO - rewardbench.rewardbench - RM inference step 188/374
+2025-05-21 11:42:23 - INFO - rewardbench.rewardbench - RM inference step 189/374
+2025-05-21 11:42:25 - INFO - rewardbench.rewardbench - RM inference step 190/374
+2025-05-21 11:42:27 - INFO - rewardbench.rewardbench - RM inference step 191/374
+2025-05-21 11:42:28 - INFO - rewardbench.rewardbench - RM inference step 192/374
+2025-05-21 11:42:30 - INFO - rewardbench.rewardbench - RM inference step 193/374
+2025-05-21 11:42:31 - INFO - rewardbench.rewardbench - RM inference step 194/374
+2025-05-21 11:42:32 - INFO - rewardbench.rewardbench - RM inference step 195/374
+2025-05-21 11:42:33 - INFO - rewardbench.rewardbench - RM inference step 196/374
+2025-05-21 11:42:34 - INFO - rewardbench.rewardbench - RM inference step 197/374
+2025-05-21 11:42:35 - INFO - rewardbench.rewardbench - RM inference step 198/374
+2025-05-21 11:42:36 - INFO - rewardbench.rewardbench - RM inference step 199/374
+2025-05-21 11:42:37 - INFO - rewardbench.rewardbench - RM inference step 200/374
+2025-05-21 11:42:38 - INFO - rewardbench.rewardbench - RM inference step 201/374
+2025-05-21 11:42:39 - INFO - rewardbench.rewardbench - RM inference step 202/374
+2025-05-21 11:42:40 - INFO - rewardbench.rewardbench - RM inference step 203/374
+2025-05-21 11:42:41 - INFO - rewardbench.rewardbench - RM inference step 204/374
+2025-05-21 11:42:43 - INFO - rewardbench.rewardbench - RM inference step 205/374
+2025-05-21 11:42:44 - INFO - rewardbench.rewardbench - RM inference step 206/374
+2025-05-21 11:42:45 - INFO - rewardbench.rewardbench - RM inference step 207/374
+2025-05-21 11:42:47 - INFO - rewardbench.rewardbench - RM inference step 208/374
+2025-05-21 11:42:48 - INFO - rewardbench.rewardbench - RM inference step 209/374
+2025-05-21 11:42:50 - INFO - rewardbench.rewardbench - RM inference step 210/374
+2025-05-21 11:42:52 - INFO - rewardbench.rewardbench - RM inference step 211/374
+2025-05-21 11:42:53 - INFO - rewardbench.rewardbench - RM inference step 212/374
+2025-05-21 11:42:54 - INFO - rewardbench.rewardbench - RM inference step 213/374
+2025-05-21 11:42:56 - INFO - rewardbench.rewardbench - RM inference step 214/374
+2025-05-21 11:42:57 - INFO - rewardbench.rewardbench - RM inference step 215/374
+2025-05-21 11:42:58 - INFO - rewardbench.rewardbench - RM inference step 216/374
+2025-05-21 11:42:59 - INFO - rewardbench.rewardbench - RM inference step 217/374
+2025-05-21 11:43:00 - INFO - rewardbench.rewardbench - RM inference step 218/374
+2025-05-21 11:43:01 - INFO - rewardbench.rewardbench - RM inference step 219/374
+2025-05-21 11:43:02 - INFO - rewardbench.rewardbench - RM inference step 220/374
+2025-05-21 11:43:03 - INFO - rewardbench.rewardbench - RM inference step 221/374
+2025-05-21 11:43:04 - INFO - rewardbench.rewardbench - RM inference step 222/374
+2025-05-21 11:43:05 - INFO - rewardbench.rewardbench - RM inference step 223/374
+2025-05-21 11:43:07 - INFO - rewardbench.rewardbench - RM inference step 224/374
+2025-05-21 11:43:09 - INFO - rewardbench.rewardbench - RM inference step 225/374
+2025-05-21 11:43:10 - INFO - rewardbench.rewardbench - RM inference step 226/374
+2025-05-21 11:43:12 - INFO - rewardbench.rewardbench - RM inference step 227/374
+2025-05-21 11:43:13 - INFO - rewardbench.rewardbench - RM inference step 228/374
+2025-05-21 11:43:15 - INFO - rewardbench.rewardbench - RM inference step 229/374
+2025-05-21 11:43:16 - INFO - rewardbench.rewardbench - RM inference step 230/374
+2025-05-21 11:43:19 - INFO - rewardbench.rewardbench - RM inference step 231/374
+2025-05-21 11:43:20 - INFO - rewardbench.rewardbench - RM inference step 232/374
+2025-05-21 11:43:22 - INFO - rewardbench.rewardbench - RM inference step 233/374
+2025-05-21 11:43:23 - INFO - rewardbench.rewardbench - RM inference step 234/374
+2025-05-21 11:43:25 - INFO - rewardbench.rewardbench - RM inference step 235/374
+2025-05-21 11:43:26 - INFO - rewardbench.rewardbench - RM inference step 236/374
+2025-05-21 11:43:27 - INFO - rewardbench.rewardbench - RM inference step 237/374
+2025-05-21 11:43:28 - INFO - rewardbench.rewardbench - RM inference step 238/374
+2025-05-21 11:43:29 - INFO - rewardbench.rewardbench - RM inference step 239/374
+2025-05-21 11:43:30 - INFO - rewardbench.rewardbench - RM inference step 240/374
+2025-05-21 11:43:31 - INFO - rewardbench.rewardbench - RM inference step 241/374
+2025-05-21 11:43:32 - INFO - rewardbench.rewardbench - RM inference step 242/374
+2025-05-21 11:43:33 - INFO - rewardbench.rewardbench - RM inference step 243/374
+2025-05-21 11:43:34 - INFO - rewardbench.rewardbench - RM inference step 244/374
+2025-05-21 11:43:35 - INFO - rewardbench.rewardbench - RM inference step 245/374
+2025-05-21 11:43:38 - INFO - rewardbench.rewardbench - RM inference step 246/374
+2025-05-21 11:43:39 - INFO - rewardbench.rewardbench - RM inference step 247/374
+2025-05-21 11:43:40 - INFO - rewardbench.rewardbench - RM inference step 248/374
+2025-05-21 11:43:42 - INFO - rewardbench.rewardbench - RM inference step 249/374
+2025-05-21 11:43:43 - INFO - rewardbench.rewardbench - RM inference step 250/374
+2025-05-21 11:43:45 - INFO - rewardbench.rewardbench - RM inference step 251/374
+2025-05-21 11:43:47 - INFO - rewardbench.rewardbench - RM inference step 252/374
+2025-05-21 11:43:49 - INFO - rewardbench.rewardbench - RM inference step 253/374
+2025-05-21 11:43:50 - INFO - rewardbench.rewardbench - RM inference step 254/374
+2025-05-21 11:43:52 - INFO - rewardbench.rewardbench - RM inference step 255/374
+2025-05-21 11:43:54 - INFO - rewardbench.rewardbench - RM inference step 256/374
+2025-05-21 11:43:55 - INFO - rewardbench.rewardbench - RM inference step 257/374
+2025-05-21 11:43:56 - INFO - rewardbench.rewardbench - RM inference step 258/374
+2025-05-21 11:43:57 - INFO - rewardbench.rewardbench - RM inference step 259/374
+2025-05-21 11:43:58 - INFO - rewardbench.rewardbench - RM inference step 260/374
+2025-05-21 11:43:59 - INFO - rewardbench.rewardbench - RM inference step 261/374
+2025-05-21 11:44:00 - INFO - rewardbench.rewardbench - RM inference step 262/374
+2025-05-21 11:44:01 - INFO - rewardbench.rewardbench - RM inference step 263/374
+2025-05-21 11:44:02 - INFO - rewardbench.rewardbench - RM inference step 264/374
+2025-05-21 11:44:03 - INFO - rewardbench.rewardbench - RM inference step 265/374
+2025-05-21 11:44:05 - INFO - rewardbench.rewardbench - RM inference step 266/374
+2025-05-21 11:44:06 - INFO - rewardbench.rewardbench - RM inference step 267/374
+2025-05-21 11:44:08 - INFO - rewardbench.rewardbench - RM inference step 268/374
+2025-05-21 11:44:10 - INFO - rewardbench.rewardbench - RM inference step 269/374
+2025-05-21 11:44:11 - INFO - rewardbench.rewardbench - RM inference step 270/374
+2025-05-21 11:44:13 - INFO - rewardbench.rewardbench - RM inference step 271/374
+2025-05-21 11:44:15 - INFO - rewardbench.rewardbench - RM inference step 272/374
+2025-05-21 11:44:17 - INFO - rewardbench.rewardbench - RM inference step 273/374
+2025-05-21 11:44:18 - INFO - rewardbench.rewardbench - RM inference step 274/374
+2025-05-21 11:44:20 - INFO - rewardbench.rewardbench - RM inference step 275/374
+2025-05-21 11:44:22 - INFO - rewardbench.rewardbench - RM inference step 276/374
+2025-05-21 11:44:23 - INFO - rewardbench.rewardbench - RM inference step 277/374
+2025-05-21 11:44:24 - INFO - rewardbench.rewardbench - RM inference step 278/374
+2025-05-21 11:44:25 - INFO - rewardbench.rewardbench - RM inference step 279/374
+2025-05-21 11:44:26 - INFO - rewardbench.rewardbench - RM inference step 280/374
+2025-05-21 11:44:27 - INFO - rewardbench.rewardbench - RM inference step 281/374
+2025-05-21 11:44:28 - INFO - rewardbench.rewardbench - RM inference step 282/374
+2025-05-21 11:44:29 - INFO - rewardbench.rewardbench - RM inference step 283/374
+2025-05-21 11:44:30 - INFO - rewardbench.rewardbench - RM inference step 284/374
+2025-05-21 11:44:31 - INFO - rewardbench.rewardbench - RM inference step 285/374
+2025-05-21 11:44:31 - INFO - rewardbench.rewardbench - RM inference step 286/374
+2025-05-21 11:44:33 - INFO - rewardbench.rewardbench - RM inference step 287/374
+2025-05-21 11:44:34 - INFO - rewardbench.rewardbench - RM inference step 288/374
+2025-05-21 11:44:35 - INFO - rewardbench.rewardbench - RM inference step 289/374
+2025-05-21 11:44:36 - INFO - rewardbench.rewardbench - RM inference step 290/374
+2025-05-21 11:44:38 - INFO - rewardbench.rewardbench - RM inference step 291/374
+2025-05-21 11:44:39 - INFO - rewardbench.rewardbench - RM inference step 292/374
+2025-05-21 11:44:41 - INFO - rewardbench.rewardbench - RM inference step 293/374
+2025-05-21 11:44:43 - INFO - rewardbench.rewardbench - RM inference step 294/374
+2025-05-21 11:44:45 - INFO - rewardbench.rewardbench - RM inference step 295/374
+2025-05-21 11:44:46 - INFO - rewardbench.rewardbench - RM inference step 296/374
+2025-05-21 11:44:49 - INFO - rewardbench.rewardbench - RM inference step 297/374
+2025-05-21 11:44:50 - INFO - rewardbench.rewardbench - RM inference step 298/374
+2025-05-21 11:44:51 - INFO - rewardbench.rewardbench - RM inference step 299/374
+2025-05-21 11:44:52 - INFO - rewardbench.rewardbench - RM inference step 300/374
+2025-05-21 11:44:53 - INFO - rewardbench.rewardbench - RM inference step 301/374
+2025-05-21 11:44:54 - INFO - rewardbench.rewardbench - RM inference step 302/374
+2025-05-21 11:44:55 - INFO - rewardbench.rewardbench - RM inference step 303/374
+2025-05-21 11:44:56 - INFO - rewardbench.rewardbench - RM inference step 304/374
+2025-05-21 11:44:57 - INFO - rewardbench.rewardbench - RM inference step 305/374
+2025-05-21 11:44:59 - INFO - rewardbench.rewardbench - RM inference step 306/374
+2025-05-21 11:45:01 - INFO - rewardbench.rewardbench - RM inference step 307/374
+2025-05-21 11:45:02 - INFO - rewardbench.rewardbench - RM inference step 308/374
+2025-05-21 11:45:04 - INFO - rewardbench.rewardbench - RM inference step 309/374
+2025-05-21 11:45:05 - INFO - rewardbench.rewardbench - RM inference step 310/374
+2025-05-21 11:45:07 - INFO - rewardbench.rewardbench - RM inference step 311/374
+2025-05-21 11:45:08 - INFO - rewardbench.rewardbench - RM inference step 312/374
+2025-05-21 11:45:11 - INFO - rewardbench.rewardbench - RM inference step 313/374
+2025-05-21 11:45:12 - INFO - rewardbench.rewardbench - RM inference step 314/374
+2025-05-21 11:45:13 - INFO - rewardbench.rewardbench - RM inference step 315/374
+2025-05-21 11:45:15 - INFO - rewardbench.rewardbench - RM inference step 316/374
+2025-05-21 11:45:17 - INFO - rewardbench.rewardbench - RM inference step 317/374
+2025-05-21 11:45:20 - INFO - rewardbench.rewardbench - RM inference step 318/374
+2025-05-21 11:45:23 - INFO - rewardbench.rewardbench - RM inference step 319/374
+2025-05-21 11:45:26 - INFO - rewardbench.rewardbench - RM inference step 320/374
+2025-05-21 11:45:29 - INFO - rewardbench.rewardbench - RM inference step 321/374
+2025-05-21 11:45:32 - INFO - rewardbench.rewardbench - RM inference step 322/374
+2025-05-21 11:45:36 - INFO - rewardbench.rewardbench - RM inference step 323/374
+2025-05-21 11:45:40 - INFO - rewardbench.rewardbench - RM inference step 324/374
+2025-05-21 11:45:42 - INFO - rewardbench.rewardbench - RM inference step 325/374
+2025-05-21 11:45:45 - INFO - rewardbench.rewardbench - RM inference step 326/374
+2025-05-21 11:45:48 - INFO - rewardbench.rewardbench - RM inference step 327/374
+2025-05-21 11:45:51 - INFO - rewardbench.rewardbench - RM inference step 328/374
+2025-05-21 11:45:54 - INFO - rewardbench.rewardbench - RM inference step 329/374
+2025-05-21 11:45:57 - INFO - rewardbench.rewardbench - RM inference step 330/374
+2025-05-21 11:46:00 - INFO - rewardbench.rewardbench - RM inference step 331/374
+2025-05-21 11:46:02 - INFO - rewardbench.rewardbench - RM inference step 332/374
+2025-05-21 11:46:04 - INFO - rewardbench.rewardbench - RM inference step 333/374
+2025-05-21 11:46:07 - INFO - rewardbench.rewardbench - RM inference step 334/374
+2025-05-21 11:46:09 - INFO - rewardbench.rewardbench - RM inference step 335/374
+2025-05-21 11:46:11 - INFO - rewardbench.rewardbench - RM inference step 336/374
+2025-05-21 11:46:13 - INFO - rewardbench.rewardbench - RM inference step 337/374
+2025-05-21 11:46:15 - INFO - rewardbench.rewardbench - RM inference step 338/374
+2025-05-21 11:46:18 - INFO - rewardbench.rewardbench - RM inference step 339/374
+2025-05-21 11:46:20 - INFO - rewardbench.rewardbench - RM inference step 340/374
+2025-05-21 11:46:22 - INFO - rewardbench.rewardbench - RM inference step 341/374
+2025-05-21 11:46:25 - INFO - rewardbench.rewardbench - RM inference step 342/374
+2025-05-21 11:46:27 - INFO - rewardbench.rewardbench - RM inference step 343/374
+2025-05-21 11:46:29 - INFO - rewardbench.rewardbench - RM inference step 344/374
+2025-05-21 11:46:31 - INFO - rewardbench.rewardbench - RM inference step 345/374
+2025-05-21 11:46:34 - INFO - rewardbench.rewardbench - RM inference step 346/374
+2025-05-21 11:46:37 - INFO - rewardbench.rewardbench - RM inference step 347/374
+2025-05-21 11:46:40 - INFO - rewardbench.rewardbench - RM inference step 348/374
+2025-05-21 11:46:41 - INFO - rewardbench.rewardbench - RM inference step 349/374
+2025-05-21 11:46:44 - INFO - rewardbench.rewardbench - RM inference step 350/374
+2025-05-21 11:46:46 - INFO - rewardbench.rewardbench - RM inference step 351/374
+2025-05-21 11:46:48 - INFO - rewardbench.rewardbench - RM inference step 352/374
+2025-05-21 11:46:50 - INFO - rewardbench.rewardbench - RM inference step 353/374
+2025-05-21 11:46:52 - INFO - rewardbench.rewardbench - RM inference step 354/374
+2025-05-21 11:46:54 - INFO - rewardbench.rewardbench - RM inference step 355/374
+2025-05-21 11:46:56 - INFO - rewardbench.rewardbench - RM inference step 356/374
+2025-05-21 11:46:59 - INFO - rewardbench.rewardbench - RM inference step 357/374
+2025-05-21 11:47:01 - INFO - rewardbench.rewardbench - RM inference step 358/374
+2025-05-21 11:47:03 - INFO - rewardbench.rewardbench - RM inference step 359/374
+2025-05-21 11:47:05 - INFO - rewardbench.rewardbench - RM inference step 360/374
+2025-05-21 11:47:07 - INFO - rewardbench.rewardbench - RM inference step 361/374
+2025-05-21 11:47:08 - INFO - rewardbench.rewardbench - RM inference step 362/374
+2025-05-21 11:47:10 - INFO - rewardbench.rewardbench - RM inference step 363/374
+2025-05-21 11:47:12 - INFO - rewardbench.rewardbench - RM inference step 364/374
+2025-05-21 11:47:13 - INFO - rewardbench.rewardbench - RM inference step 365/374
+2025-05-21 11:47:15 - INFO - rewardbench.rewardbench - RM inference step 366/374
+2025-05-21 11:47:17 - INFO - rewardbench.rewardbench - RM inference step 367/374
+2025-05-21 11:47:19 - INFO - rewardbench.rewardbench - RM inference step 368/374
+2025-05-21 11:47:21 - INFO - rewardbench.rewardbench - RM inference step 369/374
+2025-05-21 11:47:22 - INFO - rewardbench.rewardbench - RM inference step 370/374
+2025-05-21 11:47:23 - INFO - rewardbench.rewardbench - RM inference step 371/374
+2025-05-21 11:47:25 - INFO - rewardbench.rewardbench - RM inference step 372/374
+2025-05-21 11:47:26 - INFO - rewardbench.rewardbench - RM inference step 373/374
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - Results: 0.9108877721943048, on 2985 prompts
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - Mean chosen: 4.1508544998552335, std: 4.330967398045997
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - Mean rejected: -2.9946463704708233, std: 5.748473078904102
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - Mean margin: 7.145500870326057
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - alpacaeval-easy: 93/100 (0.93)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - alpacaeval-hard: 84/95 (0.8842105263157894)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - alpacaeval-length: 85/95 (0.8947368421052632)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - donotanswer: 100/136 (0.7352941176470589)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - hep-cpp: 162/164 (0.9878048780487805)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - hep-go: 153/164 (0.9329268292682927)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - hep-java: 157/164 (0.9573170731707317)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - hep-js: 157/164 (0.9573170731707317)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - hep-python: 158/164 (0.9634146341463414)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - hep-rust: 155/164 (0.9451219512195121)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - llmbar-adver-GPTInst: 82/92 (0.8913043478260869)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - llmbar-adver-GPTOut: 34/47 (0.723404255319149)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - llmbar-adver-manual: 36/46 (0.782608695652174)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - llmbar-adver-neighbor: 112/134 (0.835820895522388)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - llmbar-natural: 94/100 (0.94)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - math-prm: 393/447 (0.8791946308724832)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - mt-bench-easy: 28/28 (1.0)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - mt-bench-hard: 28/37 (0.7567567567567568)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - mt-bench-med: 39/40 (0.975)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - refusals-dangerous: 87/100 (0.87)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - refusals-offensive: 97/100 (0.97)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - xstest-should-refuse: 148/154 (0.961038961038961)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - xstest-should-respond: 237/250 (0.948)
+2025-05-21 11:47:27 - INFO - rewardbench.rewardbench - Results: {'Chat': 0.9189944134078212, 'Chat Hard': 0.8464912280701754, 'Safety': 0.904054054054054, 'Reasoning': 0.9182558520216074}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}