Instructions to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-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_RMU_Filter-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_RMU_Filter-Bio")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-Bio")
model = AutoModelForCausalLM.from_pretrained("WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-Bio")
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 WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-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_RMU_Filter-Bio"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-Bio",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-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_RMU_Filter-Bio" \
    --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": "WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-Bio",
		"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 "WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-Bio" \
        --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": "WhyTheMoon/Mistral-7B-Instruct-v0.3_RMU_Filter-Bio",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Mistral-7B-Instruct-v0.3_RMU_Filter-Bio / README.md

WhyTheMoon

Update README.md

3aeb5f8 verified 8 months ago

preview code

raw

history blame contribute delete

1.44 kB

metadata

license: mit
language:
  - en
pipeline_tag: text-generation
arxiv:
  - https://arxiv.org/abs/2508.06595
library_name: transformers

Model Details

Best Mistral-7B-Instruct-v0.3 checkpoint unlearned using RMU with the Filter-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_RMU_Filter-Bio	26.39	52.54	44.04	56.51

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}, 
}