Upload folder using huggingface_hub

README.md

@@ -0,0 +1,132 @@
+---
+license: other
+library_name: transformers
+base_model:
+- Qwen/Qwen2.5-72B-Instruct
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
+model-index:
+- name: Replete-LLM-V2.5-Qwen-72b_Duplicated
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 71.55
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 61.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 47.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 19.8
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 17.32
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 54.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
+      name: Open LLM Leaderboard
+---
+# Rombos-LLM-V2.5-Qwen-72b
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/wp9qOi2K2WGzkey0I3SgH.jpeg)
+
+Rombos-LLM-V2.5-Qwen-72b is a continues finetuned version of Qwen2.5-72B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the *Ties* merge method
+
+This version of the model shows higher performance than the original instruct and base models. 
+
+Quants: (Coming soon)
+
+GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-72b-GGUF
+
+EXL2: 
+
+Benchmarks: (Coming soon)
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rombodawg__Replete-LLM-V2.5-Qwen-72b_Duplicated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |45.39|
+|IFEval (0-Shot)    |71.55|
+|BBH (3-Shot)       |61.27|
+|MATH Lvl 5 (4-Shot)|47.58|
+|GPQA (0-shot)      |19.80|
+|MuSR (0-shot)      |17.32|
+|MMLU-PRO (5-shot)  |54.83|
+

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 29568,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 131072,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.3",
+        "bits": 6.5,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+models:
+  - model: ./qwen-72b-instruct
+    parameters:
+      weight: 1
+merge_method: ties
+base_model: ./qwen-72b
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 145412407296}, "weight_map": {"lm_head.weight": "model-00001-of-00031.safetensors", "model.embed_tokens.weight": "model-00001-of-00031.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00031-of-00031.safetensors", "model.norm.weight": "model-00031-of-00031.safetensors"}}

output-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c47a1aab65b48cad190285088e490d875368920b6ef793133a5479a02a938b
+size 8508860352

output-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823571da04e359cc589a709a8d0db004d6bb5e1621f9e5380f0a29bb6b3b365f
+size 8565768838

output-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d736abba6f07fe439239cb3adc29736a6b405a21af55f545f00cce47ab5d5159
+size 8517391816

output-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3585ee7ff5734c6c18081c2d1cfc1f9c348c9713979961fafe441f5303c5a5f
+size 8537444150

output-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a1fbb7cf94bb2a152a910ee8bf560f4f9f6b7fdcbdae600fb4376a60853e68
+size 8388945108

output-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97a44a6b7b09f0d5913e1e3a63ad8badf5426c1c7aa13e41e1f4180586b70d5
+size 8511420286

output-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b21065b4e7580bc04988ab61886ea1ec8f47720339a92927dee2805c737e247
+size 8370015892

output-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc62be0dec9929f9852dc8606f7b7ad7a438e740b03827a6685c7ea4c7ec164d
+size 1245708384

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}