初始化项目，由ModelHub XC社区提供模型

Model: RnniaSnow/ST-Coder-14B
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

Modelfile

@@ -0,0 +1,16 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant."""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,119 @@
+---
+license: mit
+library_name: transformers
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+datasets:
+- RnniaSnow/st-code-dataset
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- code
+- plc
+- iec-61131-3
+- structured-text
+- industrial-automation
+- qwen
+- llama-factory
+---
+
+# ST-Coder-14B
+
+<div align="center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers_logo_name.png" width="400"/>
+</div>
+
+## 🤖 Model Description
+
+**ST-Coder-14B** is a specialized code generation model fine-tuned on **Qwen2.5-Coder-14B-Instruct**. It is specifically optimized for **Industrial Automation** tasks, with a primary focus on the **IEC 61131-3 Structured Text (ST)** programming language.
+
+Unlike general-purpose coding models, ST-Coder-14B has been trained on high-quality, domain-specific data to understand:
+* **PLC Logic**: PID control, Motion Control, Safety logic, State Machines.
+* **IEC 61131-3 Syntax**: Correct usage of `FUNCTION_BLOCK`, `VAR_INPUT`, `VAR_OUTPUT`, and strict typing rules.
+* **Industrial Protocols**: Modbus, TCP/IP socket handling in ST, and vendor-specific nuances (Codesys, TwinCAT, Siemens SCL).
+
+## 💻 Quick Start
+
+### 1. Installation
+
+```bash
+pip install transformers torch accelerate
+```
+### 2. Inference with Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model
+model_id = "RnniaSnow/ST-Coder-14B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# Prepare the prompt
+system_prompt = "You are an expert industrial automation engineer specializing in IEC 61131-3 Structured Text."
+user_prompt = "Write a Function Block for a 3-axis motion control system with error handling."
+
+messages = [
+    {"role": "system", "content": system_prompt},
+    {"role": "user", "content": user_prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+# Generate
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=2048,
+    temperature=0.2, # Low temperature is recommended for code generation
+    top_p=0.9
+)
+
+# Decode output
+output = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(output)
+
+```
+
+### 3. Usage with vLLM (Recommended for Production)
+
+```bash
+vllm serve RnniaSnow/ST-Coder-14B --tensor-parallel-size 1 --max-model-len 8192
+
+```
+
+## 🔧 Training Details
+
+This model was trained using [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) with the following configuration:
+
+* **Base Model**: Qwen/Qwen2.5-Coder-14B-Instruct
+* **Finetuning Method**: Full LoRA Merge (Target modules: `all`)
+* **Precision**: BF16
+* **Context Window**: 8192 tokens
+* **Optimizer**: AdamW (Paged)
+* **Learning Rate Strategy**: Cosine with warmup
+
+The training data includes a mix of:
+
+1. **Golden Samples**: Verified ST code from real-world engineering projects.
+2. **Synthetic Data**: High-quality instruction-response pairs generated via DeepSeek-V3 distillation, focusing on edge cases and complex logic.
+
+## ⚠️ Disclaimer & Safety
+
+**Industrial Control Systems (ICS) carry significant physical risks.** * This model generates code based on statistical probabilities and does **not** guarantee functional correctness or safety.
+
+* **Always** verify, simulate, and test generated code in a safe environment before deploying to physical hardware (PLCs, robots, drives).
+* The authors assume no liability for any damage or injury resulting from the use of this model.
+
+## 📜 License
+
+This model is licensed under the [MIT License](https://opensource.org/licenses/MIT).

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
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf240307e18dd3fd88609f035be102377546b01568b95e616ea0c9067c81e89
+size 1966095504

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f25cf3b775a1a8d410ed747547e9e015970e24758db52b7dd95d4ef6fecbd6
+size 1919038592

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c66cca97fc353b63f753d3a92d4b1daa9d66e56580028bce78ec3b15e8347b
+size 1934731504

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f2a7a10092cbbaca848712f59feabcf7487b5192a552a8a540f5b920b67a6b
+size 1919038600

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7429d66351beb2b4ad639956a204e1a87eae9362c0f90deb5e9560adafb5dd
+size 1934731544

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c608994886da7b914b1863bcd9029d842f8251ba585a86b86256c1be9a5c0d
+size 1919038640

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f45d1aebc5e2d2ce6ec69e5e8496cdda3579a284cd5f5eaed7a00635c83b596
+size 1934731544

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5f16c8881725ce580b34e629f3f8cc7dfa341da251188dc0f3815000e871ba
+size 1919038640

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f6d5881893f6787ff34a77cb5ead4540e6b596e1fbd334b12baf2754fe4ad0
+size 1934731544

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efa527d217d6b33640b38b90be22da0ee18fc5153054278b2e57668292aa70a
+size 1919038640

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1695ddc44fa8fb2ba7e03f761e5005d4a11ec8badb94d6a9cd72fc51a1420407
+size 1934731544

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ce302da64c6d40c1552a72438cfdce010f9db04217236d9db4511325a2fbe
+size 1919038640

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac48572af8976583739ea5e4a29f9f406735df2158ad55d3b97f53cf41a3776
+size 1934731544

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614f3541e86f110d8af34384fe73103f63d1d57029e720f43319107cfcc5faf2
+size 1919038640

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19242e9110a1b48252a19d7d3db52f5f77657b08b5be95c35bd2965c1262d3bf
+size 975243264

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433848e393da9e9b9ecfec9e5d40e01d9ba52299d63cbce07e33c81f98de3d81
+size 1557135488

model.safetensors.index.json

@@ -0,0 +1,587 @@
+{
+  "metadata": {
+    "total_parameters": 14770033664,
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00016-of-00016.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.norm.weight": "model-00015-of-00016.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}