From b84c67dc426ebbf6d0d1e1f9e2bcc0f87aba0e75 Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Sun, 5 Jul 2026 03:32:16 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?=
 =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?=
 =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Model: andrevp/Nanbeige4.1-3B-MLX-BF16
Source: Original Platform
---
 .gitattributes                   |  36 ++++
 README.md                        | 346 +++++++++++++++++++++++++++++++
 added_tokens.json                |   9 +
 chat_template.jinja              | 137 ++++++++++++
 config.json                      |  33 +++
 generation_config.json           |   7 +
 model-00001-of-00002.safetensors |   3 +
 model-00002-of-00002.safetensors |   3 +
 model.safetensors.index.json     | 299 ++++++++++++++++++++++++++
 special_tokens_map.json          |  33 +++
 tokenizer.json                   |   3 +
 tokenizer.model                  |   3 +
 tokenizer_config.json            | 102 +++++++++
 tokenizer_config_search.json     | 101 +++++++++
 14 files changed, 1115 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 README.md
 create mode 100644 added_tokens.json
 create mode 100644 chat_template.jinja
 create mode 100644 config.json
 create mode 100644 generation_config.json
 create mode 100644 model-00001-of-00002.safetensors
 create mode 100644 model-00002-of-00002.safetensors
 create mode 100644 model.safetensors.index.json
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer.json
 create mode 100644 tokenizer.model
 create mode 100644 tokenizer_config.json
 create mode 100644 tokenizer_config_search.json

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..213936b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,346 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- llm
+- nanbeige
+- mlx
+- bf16
+- full-precision
+- reasoning
+- tool-calling
+- apple-silicon
+base_model: Nanbeige/Nanbeige4.1-3B
+---
+
+# Nanbeige4.1-3B-MLX-BF16 (Full Precision)
+
+This is the [Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B) model converted to [MLX](https://github.com/ml-explore/mlx) format in **full BF16 precision** (no quantization) for maximum quality inference on Apple Silicon.
+
+> **Other variants:**
+> - [andrevp/Nanbeige4.1-3B-MLX-4bit](https://huggingface.co/andrevp/Nanbeige4.1-3B-MLX-4bit) — Smallest & fastest (~2.06 GB)
+> - [andrevp/Nanbeige4.1-3B-MLX-8bit](https://huggingface.co/andrevp/Nanbeige4.1-3B-MLX-8bit) — Best balance of quality & speed (~3.91 GB)
+
+## All Variants Compared
+
+### Performance
+
+| Variant | Size | Memory | Prompt Speed | Gen Speed |
+|---------|:----:|:------:|:------------:|:---------:|
+| [4-bit](https://huggingface.co/andrevp/Nanbeige4.1-3B-MLX-4bit) | 2.06 GB | ~2.3 GB | ~279 tok/s | ~103 tok/s |
+| [8-bit](https://huggingface.co/andrevp/Nanbeige4.1-3B-MLX-8bit) | 3.91 GB | ~4.3 GB | ~342 tok/s | ~59 tok/s |
+| **BF16 (this)** | **7.35 GB** | **~8.0 GB** | **~276 tok/s** | **~33 tok/s** |
+
+### Quality Comparison (Head-to-Head, Identical Prompts, temp=0)
+
+All three variants were tested with the same prompts under deterministic settings (temperature=0) to evaluate quality differences:
+
+| Test | 4-bit | 8-bit | BF16 |
+|------|:-----:|:-----:|:----:|
+| Math: 47 * 83 | 3901 | 3901 | 3901 |
+| Logic: "All but 9 die" trick | 9 | 9 | 9 |
+| Code: Binary search | Correct | Correct | Correct |
+| Math: f(x)=2x^2-3x+1, f(5) | 36 | 36 | 36 |
+| Nuanced reasoning: Paper folding | Correct | Correct | Correct |
+| Tool call: BookFlight JSON | **Identical** | **Identical** | **Identical** |
+| AIME-style: 2^100 mod 7 | 2 | 2 | 2 |
+
+**Key findings:**
+- **8-bit vs BF16:** Produced **word-for-word identical** reasoning and answers in the majority of tests. Essentially zero quality loss.
+- **4-bit vs BF16:** Sometimes takes slightly different reasoning paths, but arrives at the **same correct answers**. Tool calling output is **100% identical** across all variants.
+- **Recommendation:** 4-bit is best for speed and memory. 8-bit is the sweet spot for quality. BF16 is for research and benchmarking where exact reproduction matters.
+
+## Original Model
+
+- **Source:** [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B)
+- **Developer:** [Nanbeige (BOSS Zhipin)](https://huggingface.co/Nanbeige)
+- **Architecture:** LlamaForCausalLM (4B parameters)
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) (same as the original model)
+
+## Conversion Details
+
+| Property | Value |
+|----------|-------|
+| Precision | BF16 (full precision) |
+| Quantization | None |
+| Model size | ~7.3 GB |
+| Conversion tool | [mlx-lm](https://github.com/ml-explore/mlx-examples/tree/main/llms) v0.30.7 |
+
+## Capabilities
+
+This model retains **all capabilities** of the original Nanbeige4.1-3B at full precision:
+
+- **Reasoning/Thinking:** Uses `<think>...</think>` tags for chain-of-thought reasoning
+- **Tool/Function Calling:** Generates structured `<tool_call>...</tool_call>` JSON output
+- **Multi-turn Conversation:** Supports multi-turn chat with context tracking
+- **Multilingual:** Strong performance in both English and Chinese
+- **Code Generation:** Capable of writing and explaining code
+- **Deep-Search Agent:** Supports deep-search tasks with 500+ rounds of tool invocations (using `tokenizer_config_search.json`)
+
+## Quickstart
+
+### Installation
+
+```bash
+pip install mlx-lm
+```
+
+### CLI Usage
+
+```bash
+mlx_lm generate \
+  --model andrevp/Nanbeige4.1-3B-MLX-4bit-BF16 \
+  --prompt "Explain quantum computing in simple terms." \
+  --max-tokens 512 \
+  --temp 0.6 \
+  --top-p 0.95
+```
+
+### Python - Chat
+
+```python
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+
+model, tokenizer = load("andrevp/Nanbeige4.1-3B-MLX-4bit-BF16")
+sampler = make_sampler(temp=0.6, top_p=0.95)
+
+messages = [
+    {"role": "user", "content": "Which number is bigger, 9.11 or 9.8?"}
+]
+prompt = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=False
+)
+response = generate(
+    model, tokenizer, prompt=prompt, max_tokens=512, sampler=sampler
+)
+print(response)
+```
+
+### Python - Tool Calling
+
+```python
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+
+model, tokenizer = load("andrevp/Nanbeige4.1-3B-MLX-4bit-BF16")
+sampler = make_sampler(temp=0.6, top_p=0.95)
+
+messages = [
+    {"role": "user", "content": "What is the weather in Tokyo?"}
+]
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "SearchWeather",
+            "description": "Find the current weather in a city.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "City name"
+                    }
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+prompt = tokenizer.apply_chat_template(
+    messages, tools=tools, add_generation_prompt=True, tokenize=False
+)
+response = generate(
+    model, tokenizer, prompt=prompt, max_tokens=256, sampler=sampler
+)
+print(response)
+```
+
+### Python - Multi-turn with Tool Responses
+
+```python
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+
+model, tokenizer = load("andrevp/Nanbeige4.1-3B-MLX-4bit-BF16")
+sampler = make_sampler(temp=0.6, top_p=0.95)
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "SearchWeather",
+            "description": "Find the current weather in a city.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {"type": "string", "description": "City name"}
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+
+messages = [
+    {"role": "user", "content": "What's the weather like in Paris?"},
+    {"role": "assistant", "content": "", "tool_calls": [
+        {"function": {"name": "SearchWeather", "arguments": '{"location": "Paris"}'}}
+    ]},
+    {"role": "tool", "content": '{"temperature": "18°C", "condition": "Partly cloudy"}'}
+]
+
+prompt = tokenizer.apply_chat_template(
+    messages, tools=tools, add_generation_prompt=True, tokenize=False
+)
+response = generate(
+    model, tokenizer, prompt=prompt, max_tokens=300, sampler=sampler
+)
+print(response)
+```
+
+## Recommended Inference Hyperparameters
+
+| Parameter | Value |
+|-----------|-------|
+| Temperature | 0.6 |
+| Top-p | 0.95 |
+| Repeat penalty | 1.0 |
+| Max new tokens | 131,072 |
+
+## Benchmarks (Original Model)
+
+### General Reasoning Tasks
+
+| Benchmark | Qwen3-4B | Qwen3-8B | Qwen3-14B | Qwen3-32B | Qwen3-30B-A3B | **Nanbeige4.1-3B** |
+|-----------|----------|----------|-----------|-----------|----------------|-------------------|
+| **Code** | | | | | | |
+| Live-Code-Bench-V6 | 57.4 | 49.4 | 55.9 | 55.7 | 66.0 | **76.9** |
+| LCB-Pro-Easy | 40.2 | 41.2 | 33.0 | 42.3 | 60.8 | **81.4** |
+| LCB-Pro-Medium | 5.3 | 3.5 | 1.8 | 3.5 | 3.5 | **28.1** |
+| **Math** | | | | | | |
+| AIME 2026 I | 81.46 | 70.42 | 76.46 | 75.83 | 87.30 | **87.40** |
+| HMMT Nov | 68.33 | 48.33 | 56.67 | 57.08 | 71.25 | **77.92** |
+| IMO-Answer-Bench | 48.00 | 36.56 | 41.81 | 43.94 | 54.34 | **53.38** |
+| **Science** | | | | | | |
+| GPQA | 65.8 | 62.0 | 63.38 | 68.4 | 73.4 | **83.8** |
+| HLE (Text-only) | 6.72 | 5.28 | 7.00 | 9.31 | 11.77 | **12.60** |
+| **Alignment** | | | | | | |
+| Arena-Hard-v2 | 34.9 | 26.3 | 36.9 | 56.0 | 60.2 | **73.2** |
+| Multi-Challenge | 41.14 | 36.30 | 36.97 | 38.72 | 49.40 | **52.21** |
+| **Tool Use** | | | | | | |
+| BFCL-V4 | 44.87 | 42.20 | 45.14 | 47.90 | 48.6 | **56.50** |
+| Tau2-Bench | 45.9 | 42.06 | 44.96 | 45.26 | 47.70 | **48.57** |
+
+### Deep Search Benchmarks
+
+| Model | xBench-DS-2505 | xBench-DS-2510 | Browse-Comp | GAIA | HLE | SEAL-0 |
+|-------|:-:|:-:|:-:|:-:|:-:|:-:|
+| MiroThinker-v1.0-8B | 61 | - | 31.1 | 66.4 | 21.5 | 40.4 |
+| AgentCPM-Explore-4B | 70 | - | 25.0 | 63.9 | 19.1 | 40.0 |
+| Qwen3-32B | 39 | 8 | 3.15 | 30.17 | 9.26 | 8.15 |
+| **Nanbeige4.1-3B** | **75** | **39** | **19.12** | **69.90** | **22.29** | **41.44** |
+
+## Files Included
+
+| File | Description |
+|------|-------------|
+| `model-00001-of-00002.safetensors` | Model weights (part 1) |
+| `model-00002-of-00002.safetensors` | Model weights (part 2) |
+| `model.safetensors.index.json` | Weight index mapping |
+| `config.json` | Model architecture configuration |
+| `tokenizer.json` | Fast tokenizer |
+| `tokenizer.model` | SentencePiece model |
+| `tokenizer_config.json` | Tokenizer config with all special tokens |
+| `tokenizer_config_search.json` | Tokenizer config for deep-search mode |
+| `chat_template.jinja` | Chat template (chat + tool calling + reasoning) |
+| `special_tokens_map.json` | Special tokens mapping |
+| `added_tokens.json` | Additional token definitions |
+| `generation_config.json` | Default generation parameters |
+
+## Special Tokens
+
+| Token | ID | Purpose |
+|-------|-----|---------|
+| `<\|im_start\|>` | 166100 | BOS / message start |
+| `<\|im_end\|>` | 166101 | EOS / message end |
+| `<\|endoftext\|>` | 166102 | End of text |
+| `<think>` | 166103 | Start of reasoning |
+| `</think>` | 166104 | End of reasoning |
+| `<tool_call>` | 166105 | Start of tool call |
+| `</tool_call>` | 166106 | End of tool call |
+
+## Deep-Search Mode
+
+For deep-search agent capabilities, switch to `tokenizer_config_search.json` and use the [miroflow-framework](https://github.com/MiroMindAI/MiroThinker) for inference. See the [original model card](https://huggingface.co/Nanbeige/Nanbeige4.1-3B) for detailed deep-search setup instructions.
+
+## Important: Extended Thinking Behavior
+
+Nanbeige4.1-3B is a **reasoning model** that generates chain-of-thought inside `<think>...</think>` tags before producing a final answer. This is by design — and it affects **all variants equally** (4-bit, 8-bit, BF16).
+
+### What to expect
+
+| Task Type | Typical Thinking Length | Recommended `max_tokens` |
+|-----------|:----------------------:|:------------------------:|
+| Math, logic, tool calling | 200–500 tokens | 512–2,048 |
+| Code generation | 500–1,500 tokens | 2,048–4,096 |
+| Translation, creative writing, commonsense | 3,000–5,000+ tokens | **8,192+** |
+
+For complex tasks (translation, creative writing, open-ended questions), the model may spend **3,000–5,000+ tokens** reasoning before delivering an answer. If `max_tokens` is too low, the output will be truncated mid-thinking and **no final answer will appear** — this is not a failure, the model simply needs more tokens to finish its thought process.
+
+### Workarounds
+
+**1. Increase `max_tokens` (recommended)**
+
+```python
+# For complex tasks, use high max_tokens
+response = generate(
+    model, tokenizer, prompt=prompt,
+    max_tokens=8192,  # or higher for very complex tasks
+    sampler=sampler
+)
+```
+
+**2. Skip thinking (experimental)**
+
+You can pre-fill an empty thinking block to force the model to answer directly. This does not always work — the model may re-enter thinking mode — but it can help for simpler open-ended tasks:
+
+```python
+prompt = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=False
+)
+prompt += '<think>\n\n</think>\n\n'  # Force empty thinking block
+response = generate(
+    model, tokenizer, prompt=prompt,
+    max_tokens=512, sampler=sampler
+)
+```
+
+**3. Post-process to extract the answer**
+
+```python
+if '</think>' in response:
+    answer = response.split('</think>')[-1].strip()
+else:
+    answer = response  # Still in thinking — increase max_tokens
+```
+
+## Limitations
+
+While safety was emphasized during training, the model may still generate unexpected outputs due to its size and probabilistic nature. Users should not propagate harmful content. The developers assume no responsibility for consequences from dissemination of inappropriate content.
+
+## License
+
+This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), the same license as the [original Nanbeige4.1-3B model](https://huggingface.co/Nanbeige/Nanbeige4.1-3B).
+
+## Credits
+
+- **Original model:** [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B) by [Nanbeige (BOSS Zhipin)](https://huggingface.co/Nanbeige)
+- **MLX framework:** [Apple MLX](https://github.com/ml-explore/mlx)
+- **Conversion:** [mlx-lm](https://github.com/ml-explore/mlx-examples/tree/main/llms)
+- **Contact (original model):** [nanbeige@kanzhun.com](mailto:nanbeige@kanzhun.com)
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..8805f6d
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,9 @@
+{
+  "</think>": 166104,
+  "</tool_call>": 166106,
+  "<think>": 166103,
+  "<tool_call>": 166105,
+  "<|endoftext|>": 166102,
+  "<|im_end|>": 166101,
+  "<|im_start|>": 166100
+}
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..6a8aa8c
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,137 @@
+
+        {%- if tools %}
+            {{- '<|im_start|>system
+' }}
+            {%- if messages[0].role == 'system' %}
+                {{- messages[0].content + '
+
+' }}
+            {%- else %} 
+                {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。
+如果没有一个函数可以使用，请直接使用自然语言回复用户。
+如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。
+如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} 
+            {%- endif %}
+            {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
+            {%- for tool in tools %}
+                {{- "
+" }}
+                {{- tool | tojson }}
+            {%- endfor %}
+            {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{\"name\": <function-name>, \"arguments\": <args-json-object>}
+</tool_call><|im_end|>
+" }}
+        {%- else %}
+            {%- if messages[0].role == 'system' %}
+                {{- '<|im_start|>system
+' + messages[0].content + '<|im_end|>
+' }}
+            {%- else %} 
+                {{- '<|im_start|>system
+你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>
+' }} 
+            {%- endif %}
+        {%- endif %}
+        {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+        {%- for message in messages[::-1] %}
+            {%- set index = (messages|length - 1) - loop.index0 %}
+            {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+                {%- set ns.multi_step_tool = false %}
+                {%- set ns.last_query_index = index %}
+            {%- endif %}
+        {%- endfor %}
+        {%- for message in messages %}
+            {%- if message.content is string %}
+                {%- set content = message.content %}
+            {%- else %}
+                {%- set content = '' %}
+            {%- endif %}
+            {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+                {{- '<|im_start|>' + message.role + '
+' + content + '<|im_end|>' + '
+' }}
+            {%- elif message.role == "assistant" %}
+                {%- set reasoning_content = '' %}
+                {%- if message.reasoning_content is string %}
+                    {%- set reasoning_content = message.reasoning_content %}
+                {%- else %}
+                    {%- if '</think>' in content %}
+                        {%- set reasoning_content = content.split('</think>')[0].rstrip('
+').split('<think>')[-1].lstrip('
+') %}
+                        {%- set content = content.split('</think>')[-1].lstrip('
+') %}
+                    {%- endif %}
+                {%- endif %}
+                {%- if loop.index0 > ns.last_query_index or keep_all_think or (extra_body is defined and extra_body.keep_all_think) %}
+                    {%- if loop.last or (not loop.last and reasoning_content) %}
+                        {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
+                    {%- else %}
+                        {{- '<|im_start|>' + message.role + '
+' + content }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '<|im_start|>' + message.role + '
+' + content }}
+                {%- endif %}
+                {%- if message.tool_calls %}
+                    {%- for tool_call in message.tool_calls %}
+                        {%- if (loop.first and content) or (not loop.first) %}
+                            {{- '
+' }}
+                        {%- endif %}
+                        {%- if tool_call.function %}
+                            {%- set tool_call = tool_call.function %}
+                        {%- endif %}
+                        {{- '<tool_call>
+{"name": "' }}
+                        {{- tool_call.name }}
+                        {{- '", "arguments": ' }}
+                        {%- if tool_call.arguments is string %}
+                            {{- tool_call.arguments }}
+                        {%- else %}
+                            {{- tool_call.arguments | tojson }}
+                        {%- endif %}
+                        {{- '}
+</tool_call>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '<|im_end|>
+' }}
+            {%- elif message.role == "tool" %}
+                {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+                    {{- '<|im_start|>user' }}
+                {%- endif %}
+                {{- '
+<tool_response>
+' }}
+                {{- content }}
+                {{- '
+</tool_response>' }}
+                {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+                    {{- '<|im_end|>
+' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endfor %}
+        {%- if add_generation_prompt %}
+            {{- '<|im_start|>assistant
+' }}
+        {%- endif %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..fbbf00c
--- /dev/null
+++ b/config.json
@@ -0,0 +1,33 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 166100,
+    "dtype": "bfloat16",
+    "embd_pdrop": 0.0,
+    "eos_token_id": 166101,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10496,
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "resid_pdrop": 0.0,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 70000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "use_cache": true,
+    "vocab_size": 166144
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..33736ee
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 166100,
+  "eos_token_id": 166101,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}
diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors
new file mode 100644
index 0000000..1045bf0
--- /dev/null
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb883639a9989df7a9d51bd78bb1545842c2ba29d29f960ac4193fdac2c8f47
+size 5367658577
diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors
new file mode 100644
index 0000000..d91b653
--- /dev/null
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aeb4d20580e8f3d120d0a59b4a1fdedc486210a5ffdf8aa8bbcd9996d7fd645
+size 2499649375
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..f4b4f00
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,299 @@
+{
+    "metadata": {
+        "total_size": 7867274240,
+        "total_parameters": 3933637120
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}
\ No newline at end of file
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..fb83292
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..f23c3b2
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8f0326910136aca20831249220b38ce5299527647bc8c6b65404485c479740
+size 18451122
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..5dc56ce
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36
+size 2782298
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..0a12a31
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,102 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166100": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166101": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166102": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166103": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166104": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166105": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166106": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/tokenizer_config_search.json b/tokenizer_config_search.json
new file mode 100644
index 0000000..cb0de17
--- /dev/null
+++ b/tokenizer_config_search.json
@@ -0,0 +1,101 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166100": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166101": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166102": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166103": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166104": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166105": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166106": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if (add_generation_prompt is defined and add_generation_prompt) %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}