Instructions to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio with Transformers:

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

pipe = pipeline("text-generation", model="WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio

SGLang

How to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio 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 "WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio with Docker Model Runner:
```
docker model run hf.co/WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio
```

Model Details

Best Mistral-7B-Instruct-v0.3 checkpoint unlearned using RR with the Keyword-Bio forget set. For more details, please check our paper.

sources

Base model: Mistral-7B-Instruct-v0.3
Repository: [https://github.com/xyzhu123/Synthetic_Textbook)

Performance

	WMDP-Bio	tinyMMLU	GSM8k	TriviaQA
Mistral-7B-Instruct-v0.3	67.48	64.20	50.19	56.81
Mistral-7B-Instruct-v0.3_RR_Keyword-Bio	49.18	63.95	47.38	57.48

Citation

If you find this useful in your research, please consider citing our paper:

@misc{zhu2025llmunlearningexpertcurated,
      title={LLM Unlearning Without an Expert Curated Dataset}, 
      author={Xiaoyuan Zhu and Muru Zhang and Ollie Liu and Robin Jia and Willie Neiswanger},
      year={2025},
      eprint={2508.06595},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.06595}, 
}

Downloads last month: 4

Safetensors

Model size

10B params

Tensor type

BF16

Collection including WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio

Synthetic Textbook

Collection

LLM Unlearning Without an Expert Curated Dataset • 39 items • Updated Oct 9, 2025

Papers for WhyTheMoon/Mistral-7B-Instruct-v0.3_RR_Keyword-Bio

LLM Unlearning Without an Expert Curated Dataset

Paper • 2508.06595 • Published Aug 8, 2025

Improving Alignment and Robustness with Short Circuiting

Paper • 2406.04313 • Published Jun 6, 2024 • 1