Add files using upload-large-folder tool

._model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8923ac779d1d13d70aab4aff8e7ba25e4e1bd20849f10d109b3c765b36bd34ca
+size 4096

._model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8923ac779d1d13d70aab4aff8e7ba25e4e1bd20849f10d109b3c765b36bd34ca
+size 4096

._model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8923ac779d1d13d70aab4aff8e7ba25e4e1bd20849f10d109b3c765b36bd34ca
+size 4096

._model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8923ac779d1d13d70aab4aff8e7ba25e4e1bd20849f10d109b3c765b36bd34ca
+size 4096

.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

README.md

@@ -0,0 +1,39 @@
+---
+license: mit
+language:
+- zh
+- en
+pipeline_tag: text-generation
+library_name: mlx
+base_model: THUDM/GLM-Z1-9B-0414
+tags:
+- mlx
+---
+
+# mlx-community/GLM-Z1-9B-0414-bf16
+
+This model [mlx-community/GLM-Z1-9B-0414-bf16](https://huggingface.co/mlx-community/GLM-Z1-9B-0414-bf16) was
+converted to MLX format from [THUDM/GLM-Z1-9B-0414](https://huggingface.co/THUDM/GLM-Z1-9B-0414)
+using mlx-lm version **0.23.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/GLM-Z1-9B-0414-bf16")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,31 @@
+{
+    "architectures": [
+        "Glm4ForCausalLM"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "eos_token_id": [
+        151329,
+        151336,
+        151338
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 13696,
+    "max_position_embeddings": 32768,
+    "model_type": "glm4",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.52.0.dev0",
+    "use_cache": true,
+    "vocab_size": 151552
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8178ce1223de398d0553af2e7f969f803b7de5757f75f14bbb601672671e9181
+size 5358668053

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15e4b507eaa85bad6a64efa566dd6f50dd7531505307ea24fd865e7fd2d94ae
+size 5336768649

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272125385d0b7a8a4eeb2de7a59c0d630cc34e5032a317ed28cebc99c2dbb4d7
+size 5303214131

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5cafb95f58e20d45f90b9bfb5c2d37b7e0af2e33372aaadd6f075ef26a1f0c1
+size 2801967421

model.safetensors.index.json

@@ -0,0 +1,530 @@
+{
+    "metadata": {
+        "total_size": 18800558080
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00004-of-00004.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.36.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.36.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.36.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.norm.weight": "model-00004-of-00004.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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 sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "chat_template": "[gMASK]<sop>{%- if tools -%}<|system|>你是一个名为 ChatGLM 的人工智能助手。你是基于智谱 AI 公司训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。\n\n# 可用工具\n\n{% for tool in tools %}{%- set function = tool.function if tool.get(\"function\") else tool %}\n\n## {{ function.name }}\n\n{{ function | tojson(indent=4, ensure_ascii=False) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。{%- endfor %}{%- endif -%}{%- for msg in messages %}{%- if msg.role == 'system' %}<|system|>\n{{ msg.content }}{%- endif %}{%- endfor %}{%- for message in messages if message.role != 'system' %}{%- set role = message['role'] %}{%- set content = message['content'] %}{%- set visible = content.split('</think>')[-1].strip() %}{%- set meta = message.get(\"metadata\", \"\") %}{%- if role == 'user' %}<|user|>\n{{ visible }}{%- elif role == 'assistant' and not meta %}<|assistant|>\n{{ visible }}{%- elif role == 'assistant' and meta %}<|assistant|>{{ meta }} \n{{ visible }}{%- elif role == 'observation' %}<|observation|>\n{{ visible }}{%- endif %}{%- endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}