Instructions to use OPTML-Group/GradDiff-SAM-WMDP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OPTML-Group/GradDiff-SAM-WMDP with Transformers:

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

pipe = pipeline("text-generation", model="OPTML-Group/GradDiff-SAM-WMDP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OPTML-Group/GradDiff-SAM-WMDP")
model = AutoModelForCausalLM.from_pretrained("OPTML-Group/GradDiff-SAM-WMDP")
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

vLLM

How to use OPTML-Group/GradDiff-SAM-WMDP with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OPTML-Group/GradDiff-SAM-WMDP

SGLang

How to use OPTML-Group/GradDiff-SAM-WMDP 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 "OPTML-Group/GradDiff-SAM-WMDP" \
    --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": "OPTML-Group/GradDiff-SAM-WMDP",
		"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 "OPTML-Group/GradDiff-SAM-WMDP" \
        --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": "OPTML-Group/GradDiff-SAM-WMDP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OPTML-Group/GradDiff-SAM-WMDP with Docker Model Runner:
```
docker model run hf.co/OPTML-Group/GradDiff-SAM-WMDP
```

GradDiff-SAM-WMDP / README.md

a-F1

Update README.md

e22b488 verified 11 months ago

preview code

raw

history blame contribute delete

1.73 kB

metadata

license: mit
datasets:
  - cais/wmdp
language:
  - en
base_model:
  - HuggingFaceH4/zephyr-7b-beta
pipeline_tag: text-generation
library_name: transformers
tags:
  - unlearn
  - machine-unlearning
  - llm-unlearning
  - data-privacy
  - large-language-models
  - trustworthy-ai
  - trustworthy-machine-learning
  - language-model

GradDiff-Unlearned w/ SAM Model on Task "WMDP"

Model Details

Unlearning:
- Task: 🤗datasets/cais/wmdp wmdp-bio
- Method: GradDiff
- Smoothness Optimization: Sharpness-aware Minimization (SAM)
Origin Model: 🤗HuggingFaceH4/zephyr-7b-beta
Code Base: github.com/OPTML-Group/Unlearn-Smooth
Research Paper: "Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond"

Loading the Model

import torch
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("OPTML-Group/GradDiff-SAM-WMDP", torch_dtype=torch.bfloat16, trust_remote_code=True)

Citation

If you use this model in your research, please cite:

@article{fan2025towards,
  title={Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond},
  author={Fan, Chongyu and Jia, Jinghan and Zhang, Yihua and Ramakrishna, Anil and Hong, Mingyi and Liu, Sijia},
  journal={arXiv preprint arXiv:2502.05374},
  year={2025}
}

Reporting Issues

Reporting issues with the model: github.com/OPTML-Group/Unlearn-Smooth