初始化项目，由ModelHub XC社区提供模型

Model: prithivMLmods/Megatron-Corpus-14B-Exp
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,192 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- prithivMLmods/Megatron-Opus-14B-Exp
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- Corpus
+- Qwen
+- trl
+model-index:
+- name: Megatron-Corpus-14B-Exp
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 49.83
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMegatron-Corpus-14B-Exp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 47.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMegatron-Corpus-14B-Exp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 34.29
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMegatron-Corpus-14B-Exp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 15.1
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMegatron-Corpus-14B-Exp
+      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: 18.85
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMegatron-Corpus-14B-Exp
+      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: 47.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FMegatron-Corpus-14B-Exp
+      name: Open LLM Leaderboard
+---
+![dsfsdf.gif](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/KRdF8fPkVNy-b7hlgUp75.gif)
+
+# **Megatron-Corpus-14B-Exp**  
+
+Megatron-Corpus-14B-Exp is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. It has been fine-tuned on a synthetic dataset based on math corpus, further optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex reasoning tasks, instruction-following, and text generation.  
+
+### **Key Improvements**  
+1. **Advanced Reasoning & Logic**: Optimized for multi-step problem-solving, logical deduction, and contextual analysis.  
+2. **Fine-Tuned Instruction Following**: Generates precise responses, structured outputs (e.g., JSON), and extended long-form text (8K+ tokens).  
+3. **Greater Adaptability**: Excels in role-playing, multi-turn dialogues, and diverse system prompts.  
+4. **Long-Context Support**: Handles up to **128K tokens** and generates up to **8K tokens** per output.  
+5. **Multilingual Proficiency**: Supports over **29 languages**, including Chinese, English, French, Spanish, Portuguese, German, and more.  
+
+### **Quickstart with Transformers**  
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "prithivMLmods/Megatron-Corpus-14B-Exp"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Explain the concept of logical reasoning in AI."
+messages = [
+    {"role": "system", "content": "You are an expert AI assistant specialized in reasoning and logic."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+
+### **Intended Use**  
+- **Advanced Logical & Analytical Reasoning**: Designed for problem-solving, multi-step deductions, and cognitive reasoning tasks.  
+- **Mathematical & Scientific Computation**: Supports theorem proving, complex calculations, and scientific knowledge retrieval.  
+- **Code Generation & Debugging**: Generates optimized code, detects errors, and improves programming workflows.  
+- **Structured Data Analysis**: Processes tables, JSON, and structured formats for data-centric applications.  
+- **Multilingual Reasoning & Translation**: High proficiency across **29+ languages** for international applications.  
+- **Extended Text Generation**: Capable of generating research papers, instructional guides, and in-depth reports.  
+
+### **Limitations**  
+1. **High Computational Requirements**: Due to its **14B parameters** and **128K context support**, it requires powerful GPUs or TPUs for efficient inference.  
+2. **Language-Specific Variability**: Performance may differ across supported languages, especially for low-resource languages.  
+3. **Potential Error Accumulation**: Long-form text generation can introduce inconsistencies over extended outputs.  
+4. **Limited Real-World Awareness**: Knowledge is restricted to training data and may not reflect recent world events.  
+5. **Prompt Sensitivity**: The quality of responses depends on the specificity and clarity of the input prompt.
+# [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/prithivMLmods__Megatron-Corpus-14B-Exp-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=prithivMLmods%2FMegatron-Corpus-14B-Exp&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    35.55|
+|IFEval (0-Shot)    |    49.83|
+|BBH (3-Shot)       |    47.92|
+|MATH Lvl 5 (4-Shot)|    34.29|
+|GPQA (0-shot)      |    15.10|
+|MuSR (0-shot)      |    18.85|
+|MMLU-PRO (5-shot)  |    47.33|
+

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": "prithivMLmods/Megatron-Corpus-14B-Exp",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 151645,
+  "max_length": 131072,
+  "pad_token_id": 151643,
+  "transformers_version": "4.47.1",
+  "use_cache": false
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c12d1b3c0e1b26b8a0f8d0e6a5d6213a63b2266cc01e3fe9e60aa1c9a31373
+size 4982125440

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9baaf9785813d9e6a36e8ded24d4ccb3807f909a14d0db39cbb52cc49f117f4
+size 4954847240

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b4191a2add7b2a0e132f72de33414f084c9bfeac6af310e85fe1569a5c9500
+size 4954847280

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71aa864b1df59315988bb1ba57325509d760cc716d3cdd9201173b92537a1cad
+size 4954847280

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3413a78f16745bbe83954c10700a393872cceab2ee4754e09d2a1a801046cf
+size 4954847280

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a4b217917f5da83f9738258b487f86fe838d98344d16502cbfd8bd4acd22c9
+size 4730447336

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+    "metadata": {
+        "total_size": 29531895808
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00006-of-00006.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.norm.weight": "model-00006-of-00006.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 +1,209 @@
+{
+  "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\") %}            {{- '<|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",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}