---
license: other
base_model: Qwen/Qwen3-8B
library_name: transformers
pipeline_tag: text-generation
tags:
  - qwen3
  - causal-lm
  - transformers
language:
  - zh
  - en
arxiv: 2606.30345
github: https://github.com/LianjiaTech/drift
blog: https://lianjiatech.github.io/drift/blog/
---

# Drift-8B-ToolUse

<!-- 顶部快速跳转徽标 -->
[![github](https://img.shields.io/badge/GitHub-Repository-blue?logo=github)](https://github.com/LianjiaTech/drift)
[![blog](https://img.shields.io/badge/Blog-Post-orange?logo=blogger)](https://lianjiatech.github.io/drift/blog/)
[![arxiv](https://img.shields.io/badge/arXiv-2606.30345-b31b1b.svg?logo=arxiv)](https://arxiv.org/abs/2606.30345)

This repository contains a merged HuggingFace checkpoint fine-tuned based on `Qwen/Qwen3-8B`.

## Quick Links

- **GitHub Repository**: [LianjiaTech/drift](https://github.com/LianjiaTech/drift)
- **Technical Blog**: [DRIFT Blog](https://lianjiatech.github.io/drift/blog/)
- **Academic Paper**: [arXiv:2606.30345](https://arxiv.org/abs/2606.30345)

## Model Summary

- Base model: `Qwen/Qwen3-8B`
- Architecture: `Qwen3ForCausalLM`
- Precision: `bfloat16`
- Context length (config): `max_position_embeddings = 40960`
- Weights format: sharded `safetensors` (4 shards)

## Usage

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Yiwei6534/Drift-8B-ToolUse"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What can you help me with?"},
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Generation Defaults

The bundled `generation_config.json` uses `temperature=0.6`, `top_k=20`, `top_p=0.95`. Adjust based on your deployment.

## Integrity Files

- `FILE_MANIFEST.json`: list of distributed files and their byte sizes.
- `SHA256SUMS.txt`: SHA256 checksums for all distributed files (verify with `sha256sum -c SHA256SUMS.txt`).

## Limitations

- The model may hallucinate tool calls or produce invalid arguments.
- Output quality depends on the serving template and tool schema formatting.
- Safety, bias, and domain-specific failure modes are not fully documented here.

## Citation

If you find DRIFT or this model helpful in your research, please cite:

```bibtex
@article{luo2026drift,
  title={DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training},
  author={Luo, Haisen and Liu, Yiwei and Wang, Haoning and Liu, Dan and Yin, Junxi and Wang, Haotian and Zhang, Lei and Tian, Xiaoyu and Chen, Shuaiting and Song, Yuansheng and others},
  journal={arXiv preprint arXiv:2606.30345},
  year={2026}
}
```

## License

This repository uses `license: other` as a placeholder. Replace it with the correct license for the base model, your fine-tuning data, and your distribution terms before publishing.