Instructions to use linglingdan/DRIFT-8B-ToolUse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use linglingdan/DRIFT-8B-ToolUse with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="linglingdan/DRIFT-8B-ToolUse")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("linglingdan/DRIFT-8B-ToolUse")
model = AutoModelForCausalLM.from_pretrained("linglingdan/DRIFT-8B-ToolUse")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use linglingdan/DRIFT-8B-ToolUse with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "linglingdan/DRIFT-8B-ToolUse"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linglingdan/DRIFT-8B-ToolUse",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/linglingdan/DRIFT-8B-ToolUse

SGLang

How to use linglingdan/DRIFT-8B-ToolUse with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "linglingdan/DRIFT-8B-ToolUse" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linglingdan/DRIFT-8B-ToolUse",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "linglingdan/DRIFT-8B-ToolUse" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linglingdan/DRIFT-8B-ToolUse",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use linglingdan/DRIFT-8B-ToolUse with Docker Model Runner:
```
docker model run hf.co/linglingdan/DRIFT-8B-ToolUse
```

Drift-8B-ToolUse

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

Quick Links

GitHub Repository: LianjiaTech/drift
Technical Blog: DRIFT Blog
Academic Paper: arXiv: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

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:

@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.