README.md

---
library_name: transformers
license: mit
base_model: Qwen/Qwen3-4B-Instruct-2507
tags:
  - code
  - agent
  - tool-calling
  - distillation
  - qwen3
  - ms-swift
  - codebase-analysis
language:
  - en
pipeline_tag: text-generation
---

<div align="center">
  <img src="assets/locotrainer.png" width="55%" alt="LocoTrainer" />
</div>

<br>

<div align="center">

[![PyPI](https://img.shields.io/badge/PyPI-3775A9?style=for-the-badge&logo=pypi&logoColor=white)](https://pypi.org/project/locotrainer/)
[![MODEL](https://img.shields.io/badge/Model-FFB300?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/LocoreMind/LocoTrainer-4B)
[![GGUF](https://img.shields.io/badge/GGUF-FF6F00?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/LocoreMind/LocoTrainer-4B-GGUF)
[![Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&logoColor=white)](https://colab.research.google.com/github/LocoreMind/LocoTrainer/blob/main/LocoTrainer_4B.ipynb)
[![GitHub](https://img.shields.io/badge/GitHub-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/LocoreMind/LocoTrainer)

</div>

## Introduction

**LocoTrainer-4B** is a 4B-parameter MS-SWIFT domain expert agent trained via knowledge distillation from **Qwen3-Coder-Next**. Unlike general-purpose code agents, it combines multi-turn tool-calling with deep MS-SWIFT framework knowledge — enabling it to analyze codebases and generate comprehensive markdown reports without a separate reasoning model.

## Demo

<div align="center">
  <img src="assets/demo.gif" width="90%" alt="LocoTrainer Demo" />
</div>

*LocoTrainer analyzing MS-SWIFT codebase with LocoTrainer-4B model via vLLM*

|  | LocoTrainer-4B |
|:--|:--|
| **Base Model** | [Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) |
| **Teacher Model** | Qwen3-Coder-Next |
| **Training Method** | Full-parameter SFT (distillation) |
| **Training Data** | 361,830 samples (agent trajectory + MS-SWIFT knowledge + project paths) |
| **Max Sequence Length** | 32,768 tokens |
| **Training Hardware** | 8x NVIDIA H100 80GB |
| **Training Time** | ~25 hours |
| **Framework** | MS-SWIFT |

## Key Features

- **MS-SWIFT Domain Expert**: Trained on MS-SWIFT documentation, CLI parameters, and project structure paths — answers framework questions accurately
- **Tool-Calling Agent**: Generates structured `<tool_call>` JSON for Read, Grep, Glob, Bash, and Write tools
- **End-to-End Reports**: From a single question to a complete, well-structured markdown analysis report
- **Long Context**: 32K training covers 90% of long-context analysis scenarios
- **Local Deployment**: GGUF quantized version available for zero API cost inference

## Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "LocoreMind/LocoTrainer-4B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

messages = [
    {
        "role": "system",
        "content": "You are Claude Code, Anthropic's official CLI for Claude.\n\nYou are an interactive agent that helps users with software engineering tasks.\n\nCRITICAL CONSTRAINTS:\n1. ALWAYS use absolute file paths in tool calls.\n2. EFFICIENCY: Use multiple tool calls to explore the codebase.\n3. OUTPUT: Save your findings as a well-structured markdown document.\n\nENV: Working directory is /Users/developer/workspace (macOS, zsh)."
    },
    {
        "role": "user",
        "content": "What are the default LoRA settings in ms-swift?\n\nAnalyze the codebase at /Users/developer/workspace/ms-swift and save your findings as a well-structured markdown document to /Users/developer/workspace/output/output.md."
    }
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024,
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)
print(content)
```

## LocoTrainer Framework

LocoTrainer-4B is designed to run inside the **LocoTrainer agent framework**, which handles the full agent loop — tool execution, multi-turn conversation, and report generation.

```bash
pip install locotrainer

locotrainer run -q "What are the default LoRA settings in ms-swift?"
# → output/output.md
```

For full setup and usage, refer to the [GitHub repository](https://github.com/LocoreMind/LocoTrainer).

## Training Details

| Parameter | Value |
|:----------|:------|
| Base model | Qwen3-4B-Instruct-2507 |
| Teacher model | Qwen3-Coder-Next |
| Method | Full-parameter SFT |
| Training data | 361,830 samples |
| Data composition | Agent trajectory + MS-SWIFT knowledge + project structure paths |
| Hardware | 8x NVIDIA H100 80GB |
| DeepSpeed | ZeRO-2 |
| Precision | BF16 |
| Epochs | 1 |
| Max sequence length | 32,768 tokens |
| Attention | Flash Attention 2 |
| Kernel optimization | Liger Kernel |
| Learning rate | 1e-5, warmup ratio 0.05 |
| Batch size | 1/GPU, gradient accumulation 4 (effective batch 32) |
| Template | qwen3_nothinking |
| Framework | MS-SWIFT |
| Training time | ~25 hours |

## Known Limitations

- Specialized for MS-SWIFT; performance on unrelated codebases is untested
- 4B parameters — complex multi-hop reasoning may require a larger model
- MS-SWIFT project structure knowledge reflects the training data snapshot; may drift as the framework evolves

## License

MIT

## Acknowledgments

- [Qwen Team](https://huggingface.co/Qwen) for the Qwen3-4B-Instruct-2507 base model
- [MS-SWIFT](https://github.com/modelscope/ms-swift) for the training framework and the codebase this model specializes in
- [llama.cpp](https://github.com/ggerganov/llama.cpp) for efficient local inference
- [Anthropic](https://www.anthropic.com/) for the Claude Code agent loop design that inspired this work