Upload model

.gitattributes

@@ -44,4 +44,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* 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 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,29 @@
+{
+  "_name_or_path": "/mnt/pfs/nlp/wulixin/exp_dir_etuning_reason/etuning-reason-qwq-sft-qwen25-14b-exp1-2-2024.12.06-12:35:05/models/checkpoint-352",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf28cee065623a346b6701fc1fac2a353a12181253e6d05b46fceb50b2d6b2b7
+size 3885134104

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a32aadff94f410e5674934340d89cc0bc5c36feade108721c8bb04a1fb7ca38
+size 3995327992

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf7c1ad327ea30f3badb22fe7fcad64c0ba569ce6f0863761e05b9190fe92de
+size 3995328064

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d0f2533c429bd3b183eb5c38869ba97a05ff64b990426d4088a1e4dd7072bf
+size 3995348776

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2c897b85f1c6445f3c84b5d6820534f64bede9411c3c463404c42768b27551
+size 3979614448

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d0e0c3c6f874f5587ed71d6a60c43f351f41eca3572ed4f3c45e13df373a3e
+size 3995328064

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880236541c79a22cea562bc72fe70ee3c4eeece85c95b6723f16dfd42b48713a
+size 3995328064

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294fafbc284d7b8dd57e478987bd378123abd618bbc2e58da051a23f85b336b1
+size 1698724408

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}

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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}