初始化项目，由ModelHub XC社区提供模型

Model: ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,285 @@
+---
+license: apache-2.0
+base_model: openbmb/MiniCPM5-1B
+tags:
+- minicpm
+- minicpm5
+- minicpm5-1b
+- tool-calling
+- function-calling
+- tool-use
+- agentic
+- agentic-ai
+- ai-agent
+- xml-tool-calling
+- json-function-calling
+- merged-model
+- full-finetune
+- unsloth
+- openbmb
+- llama
+- text-generation
+- conversational
+- small-language-model
+- slm
+- edge-ai
+- on-device
+- local-llm
+- vllm
+- sglang
+- transformers
+language:
+- en
+pipeline_tag: text-generation
+datasets:
+- Team-ACE/ToolACE
+model-index:
+- name: MiniCPM5-1B-Agentic-Tooluse-v3
+  results:
+  - task:
+      type: text-generation
+      name: Tool calling
+    dataset:
+      name: External ToolACE-derived first-call evaluation (held-out 300 examples)
+      type: Team-ACE/ToolACE
+    metrics:
+    - type: parseable_rate
+      value: 1.0000
+      name: Parseable tool-call rate
+    - type: valid_name_rate
+      value: 0.9867
+      name: Valid available-tool name rate
+    - type: expected_name_rate
+      value: 0.9533
+      name: Expected tool-name rate
+    - type: args_exact_rate
+      value: 0.7467
+      name: Exact-arguments rate
+    - type: arg_key_overlap
+      value: 0.9388
+      name: Argument-key overlap
+    - type: no_schema_copy_rate
+      value: 0.9967
+      name: No-schema-copy rate
+    - type: no_repetition_rate
+      value: 0.3400
+      name: No-repetition rate
+    - type: stopped_cleanly_rate
+      value: 0.0000
+      name: Stopped-cleanly rate
+---
+
+# MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16 — Small Function-Calling LLM for vLLM / SGLang / Transformers
+
+**MiniCPM5-1B-Agentic-Tooluse-v3** is a **1-billion-parameter open-weight function-calling model** merged into a single full-precision FP16 checkpoint — no adapter loading, no PEFT setup, no extra dependencies. Load it directly with `transformers`, serve it with **vLLM** or **SGLang**, and start calling tools immediately.
+
+If you are looking for a **small function-calling LLM for production serving**, a **1B tool-use model for vLLM or SGLang**, a **compact open-weight alternative to GPT-4o / Claude function calling**, or a **locally deployable structured-output model for agent pipelines**, this is the single-file, deploy-anywhere version.
+
+> **74.67% exact-argument accuracy** on a held-out 300-example benchmark — trained with QLoRA supervised fine-tuning followed by GRPO reinforcement learning, rewarding exact function-name and argument-value correctness.
+
+## Why this model
+
+MiniCPM5-1B-Agentic-Tooluse-v3 is fine-tuned specifically to parse a tool schema and a natural-language user request, then emit a structured, correctly-named, correctly-valued function call — the exact skill that powers LangChain agents, LlamaIndex pipelines, AutoGen, CrewAI, MCP tool servers, ReAct loops, and home-automation assistants.
+
+Unlike most small open tool-calling models that stop at supervised fine-tuning, this model goes further with **GRPO reinforcement learning** on top of the SFT checkpoint, specifically rewarding the two hardest parts of tool calling: choosing the right function name and getting every argument value exactly right.
+
+**Compared to GPT-4o / Claude for function calling:** this model is 100% free, runs locally, keeps all data private, has zero per-call cost, and is fine-tunable — it trades some absolute accuracy for massive gains in cost, latency, and privacy. The merged FP16 format means you can load it with a single `AutoModelForCausalLM.from_pretrained()` call, just like any base model.
+## Why this model
+
+MiniCPM5-1B-Agentic-Tooluse-v3 is fine-tuned specifically for **agentic tool/function calling**: given a tool schema and a natural-language request, it reliably produces a correctly-named, correctly-structured, correctly-valued function call — the exact capability that powers LangChain/LlamaIndex/AutoGen/CrewAI agents, MCP tool servers, ReAct-style loops, and home-automation assistants.
+
+This release combines **QLoRA supervised fine-tuning** with a **GRPO reinforcement-learning refinement stage**, specifically optimized to improve exact function-name selection and exact argument-value correctness — historically the two hardest failure modes for small (~1B) tool-calling models.
+
+## Results
+
+Evaluated on a held-out 300-example test slice drawn from a **seeded shuffle** of ToolACE (see *Split integrity*).
+The base-model column is the same model with the same prompt and no adapter.
+
+The **published weights are SFT + GRPO** (see *GRPO / RLVR*). The SFT column is kept because every
+negative result below is measured against it.
+
+| metric | v2 (previous release) | SFT retrain (pre-GRPO) | **v3 = SFT + GRPO (published)** |
+|---|---|---|---|
+| `parseable` — output is a well-formed call | 0.9933 | 1.0000 | **1.0000** |
+| `valid_name` — name exists among the offered tools | 0.9700 | 0.9867 | **0.9867** |
+| `expected_name` — name matches gold | 0.9067 | 0.9567 | **0.9533** |
+| `args_exact` — *every* argument value matches gold | 0.6133 | 0.7367 | **0.7467** |
+| `arg_key_overlap` — F1 over argument keys | 0.8757 | 0.9422 | **0.9388** |
+| **mean of 5** | 0.8718 | 0.9245 | **0.9251** |
+
+GRPO buys +0.0100 on `args_exact`, the metric that matters here, and gives back 0.0034 (one test example
+each) on `expected_name` and `arg_key_overlap`. That trade is reported rather than hidden: the mean moves
+only +0.0006, so this is a targeted gain on the hardest metric, not a broad improvement.
+
+## Full 8-metric benchmark (held-out test set, n=300)
+
+This table mirrors the evaluation format from v2 and shows Base, v2, and v3 side-by-side
+across all 8 metrics using a single consistent harness and held-out test slice:
+
+| Metric | Base MiniCPM5-1B | v2 (previous release) | v3 (this model) | Delta (v2 → v3) |
+|---|---:|---:|---:|---:|
+| parseable_rate | 0.0133 | 0.9933 | 1.0000 | +0.0067 |
+| valid_name_rate | 0.0133 | 0.9700 | 0.9867 | +0.0167 |
+| expected_name_rate | 0.0133 | 0.9267 | 0.9533 | +0.0267 |
+| args_exact_rate | 0.1500 | 0.6533 | 0.7467 | +0.0934 |
+| arg_key_overlap | 0.0033 | 0.7517 | 0.9388 | +0.1871 |
+| no_schema_copy_rate | 1.0000 | 1.0000 | 0.9967 | -0.0033 |
+| no_repetition_rate | 0.9967 | 1.0000 | 0.3400 | -0.6600 |
+| stopped_cleanly_rate | 0.0000 | 0.1500 | 0.0000 | -0.1500 |
+
+**What the additional metrics mean:**
+- `no_schema_copy_rate` — the model did **not** copy the tool schema's own field description
+  verbatim into an argument value.
+- `no_repetition_rate` — the completion did not contain a duplicated function-call block or
+  degenerate repeated-phrase loop. This model has a known weakness here: it often continues
+  generating filler content after the tool call completes. Use a parser that extracts the first
+  completed `<function>...</function>` block.
+- `stopped_cleanly_rate` — the model naturally stopped immediately after the completed
+  `</function>` tag with no trailing tokens. Use a parser that treats the first completed
+  `<function>...</function>` block as the action boundary — do not rely on natural end-of-generation.
+
+## Model details
+
+- **Base model:** [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)
+
+- **Architecture:** Llama-style causal language model, ~1.08B parameters
+
+- **Format:** merged full weights, safetensors, FP16 — no adapter/PEFT loading required
+
+- **Training pipeline:** QLoRA SFT on tool-calling trajectories → GRPO reinforcement learning targeting exact argument correctness
+
+- **Compatible with:** `transformers`, vLLM, SGLang, TGI, and any standard Hugging Face causal-LM serving pipeline
+
+## Quickstart
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16")
+
+model = AutoModelForCausalLM.from_pretrained("ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16")
+
+# Use tok.apply_chat_template(messages, tools=[...]) with your function/tool schema,
+
+# then generate as usual — the model emits a structured function call.
+
+```
+
+**vLLM:**
+
+```bash
+
+vllm serve ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16
+
+```
+
+## Ideal use cases
+
+- Production agent backends that need a fast, cheap, self-hosted function-calling model
+
+- LangChain / LlamaIndex / AutoGen / CrewAI / MCP-based agents needing a small, reliable tool-calling backbone
+
+- On-device and edge deployments where a 7B+ model isn't an option
+
+- High-throughput services where per-request cost and latency matter more than squeezing out the last few points of accuracy from a much larger model
+
+- Teams that want a fully open-weight, fine-tunable starting point instead of depending on a closed API for structured tool calls
+
+## Base model architecture
+
+MiniCPM5-1B uses a standard `LlamaForCausalLM` architecture:
+
+| Property | Value |
+|---|---|
+| Parameters (total) | 1,080,632,832 |
+| Parameters (non-embedding) | 679,552,512 |
+| Architecture | `LlamaForCausalLM` |
+| Layers | 24 |
+| Attention heads (GQA) | 16 Q / 2 KV |
+| Context length | 131,072 tokens |
+| Training | SFT → RL (GRPO) fine-tune on [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) |
+
+## Thinking mode
+
+MiniCPM5-1B has a built-in `<think>...</think>` chat template. The same checkpoint can act as a fast assistant **or** a deliberate chain-of-thought reasoner — controlled by a single flag:
+
+```python
+# Fast mode — recommended for tool calling (thinking OFF)
+prompt = tokenizer.apply_chat_template(
+    messages, tools=tools, add_generation_prompt=True,
+    enable_thinking=False,
+    tokenize=False,
+)
+
+# Reasoning mode (thinking ON — NOT recommended for tool calling)
+prompt = tokenizer.apply_chat_template(
+    messages, tools=tools, add_generation_prompt=True,
+    enable_thinking=True,
+    tokenize=False,
+)
+```
+
+> **Important:** always use `enable_thinking=False` for tool/function calling. With thinking ON the model spends its token budget inside `<think>...</think>` and may not reach a completed function call. All benchmark numbers in this card use thinking OFF.
+
+## Citation
+
+If you use this model, please cite the base model paper:
+
+```bibtex
+@article{minicpm4,
+  title   = {MiniCPM4: Ultra-Efficient LLMs on End Devices},
+  author  = {MiniCPM Team},
+  journal = {arXiv preprint arXiv:2506.07900},
+  year    = {2025}
+}
+```
+
+And the ToolACE dataset used for fine-tuning:
+
+```bibtex
+@article{toolace,
+  title   = {ToolACE: Winning the Points of LLM Function Calling},
+  author  = {Liu, Ying and others},
+  journal = {arXiv preprint arXiv:2409.00920},
+  year    = {2024}
+}
+```
+
+## ModelScope
+
+The base model is also available on ModelScope (for users in China and East Asia):
+
+- [OpenBMB/MiniCPM5-1B on ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B)
+
+*(The fine-tuned adapter/GGUF builds are currently HuggingFace-only.)*
+## Related repos
+
+### v3 model family (this release)
+
+| Format | Repository |
+|--------|-----------|
+| LoRA adapter (PEFT, smallest download, fine-tune further) | [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3) |
+| Merged full-weight FP16 (transformers / vLLM / SGLang serving) | [MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16) |
+| GGUF quantizations (llama.cpp / Ollama / LM Studio, CPU-friendly) | [MiniCPM5-1B-Agentic-Tooluse-v3-GGUF](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF) |
+
+### Previous releases
+
+| Format | Repository |
+|--------|-----------|
+| v2 LoRA adapter | [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2) |
+| v2 Merged FP16 | [MiniCPM5-1B-Agentic-Tooluse-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16) |
+| v2 GGUF | [MiniCPM5-1B-Agentic-Tooluse-GGUF](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-GGUF) |
+## FAQ
+
+**Do I need the adapter repo too?** No — this repo already contains the fully merged weights. Use the adapter repo only if you want to load it on top of base MiniCPM5-1B yourself or continue fine-tuning.
+
+**What's the difference between this and the GGUF repo?** This is full-precision FP16 safetensors for GPU-backed serving frameworks (`transformers`, vLLM, SGLang). The GGUF repo is quantized for CPU-friendly local inference via llama.cpp/Ollama/LM Studio.
+
+**How was v3 trained differently from v2?** v3 continues from the v2-era recipe with an additional QLoRA SFT pass plus a GRPO reinforcement-learning stage explicitly rewarding exact argument-value correctness, which is what drives the args_exact improvement shown above.
+
+## Base model
+
+Built on [MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) by OpenBMB.
+
+## Limitations

chat_template.jinja

@@ -0,0 +1,179 @@
+{{- bos_token }}{%- if tools %}
+    {%- set tool_definitions %}
+        {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+        {%- for tool in tools %}
+            {{- "\n" }}
+            {{- tool | tojson(ensure_ascii=False) }}
+        {%- endfor %}
+        {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
+    {%- endset %}
+    
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if '<tool_def_sep>' in messages[0].content %}
+            {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
+        {%- else %}
+            {{- messages[0].content + '\n\n' + tool_definitions }}
+        {%- endif %}
+    {%- else %}
+        {{- tool_definitions.lstrip() }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- 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 + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- 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('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        
+        {%- if message.tool_calls %}
+            {%- set content_parts = content.split('<tool_sep>') %}
+            {%- set processed_content = content_parts[0] %}
+            {%- set tool_calls_count = message.tool_calls|length %}
+            {%- set tool_sep_count = content_parts|length - 1 %}
+            {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
+            
+            {%- for i in range(1, content_parts|length) %}
+                {%- set tool_index = i - 1 %}
+                {%- if tool_index < tool_calls_count %}
+                    {%- set tool_call = message.tool_calls[tool_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set single_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
+                {%- else %}
+                    {%- set processed_content = processed_content + content_parts[i] %}
+                {%- endif %}
+            {%- endfor %}
+            
+            {%- if tool_calls_count > tool_sep_count %}
+                {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
+                    {%- set tool_call = message.tool_calls[remaining_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set remaining_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + remaining_tool_xml %}
+                {%- endfor %}
+            {%- endif %}
+            
+            {%- set content = processed_content %}
+        {%- endif %}
+        
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if reasoning_content %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        
+        {%- if message.tool_calls and not has_tool_sep %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<function name="' ~ tool_call.name ~ '">' }}
+                {%- if tool_call.arguments %}
+                    {%- set args_dict = tool_call.arguments %}
+                    {%- for param_name, param_value in args_dict.items() %}
+                        {{- '<param name="' ~ param_name ~ '">' }}
+                        {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                            {{- '<![CDATA[' + param_value + ']]>' }}
+                        {%- else %}
+                            {{- param_value }}
+                        {%- endif %}
+                        {{- '</param>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- content }}
+        {%- else %}
+            {{- message.content | tojson(ensure_ascii=False) }}
+        {%- endif %}
+        {{- '\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' }}
+    {%- if enable_thinking is defined %}
+        {%- if enable_thinking is false %}
+            {{- '<think>\n\n</think>\n\n' }}
+        {%- elif enable_thinking is true %}
+            {{- '<think>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float16",
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 130560
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "pad_token_id": 1,
+  "temperature": 0.9,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d777ad58a6c4875b3fd08e80a6147257c340a3df593d41995c69e3a84ccfd4
+size 2161290720

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}