Instructions to use OPTML-Group/SimNPO-WMDP-zephyr-7b-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OPTML-Group/SimNPO-WMDP-zephyr-7b-beta with Transformers:

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

pipe = pipeline("text-generation", model="OPTML-Group/SimNPO-WMDP-zephyr-7b-beta")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OPTML-Group/SimNPO-WMDP-zephyr-7b-beta")
model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-WMDP-zephyr-7b-beta")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OPTML-Group/SimNPO-WMDP-zephyr-7b-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OPTML-Group/SimNPO-WMDP-zephyr-7b-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OPTML-Group/SimNPO-WMDP-zephyr-7b-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OPTML-Group/SimNPO-WMDP-zephyr-7b-beta

SGLang

How to use OPTML-Group/SimNPO-WMDP-zephyr-7b-beta 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/SimNPO-WMDP-zephyr-7b-beta" \
    --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": "OPTML-Group/SimNPO-WMDP-zephyr-7b-beta",
		"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 "OPTML-Group/SimNPO-WMDP-zephyr-7b-beta" \
        --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": "OPTML-Group/SimNPO-WMDP-zephyr-7b-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OPTML-Group/SimNPO-WMDP-zephyr-7b-beta with Docker Model Runner:
```
docker model run hf.co/OPTML-Group/SimNPO-WMDP-zephyr-7b-beta
```

SimNPO-Unlearned Model on Task "WMDP"

Model Details

Unlearning:
- Task: 🤗datasets/cais/wmdp
- Method: SimNPO
Origin Model: 🤗HuggingFaceH4/zephyr-7b-beta
Code Base: github.com/OPTML-Group/Unlearn-Simple
Research Paper: "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"

Unlearning Algorithm

This model uses the SimNPO unlearning algorithm with the following optimization objective: $\ell_{SimNPO}(\mathbf{\theta}) = \mathbb{E}_{(x, y) \in \mathcal{D}_f}\left[-\frac{2}{\beta}\log\sigma\left(-\frac{\beta}{|y|}\log\pi_{\mathbf{\theta}}(y|x) - \gamma\right)\right] + \lambda \mathbb{E}_{(x, y) \in \mathcal{D}_r}[-\log\pi_{\mathbf{\theta}} (y|x)]$ Unlearning hyper-parameters:

Learning Rate: 4e-6
beta: 5.5
lambda: 5.0
gamma: 0.0

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-WMDP-zephyr-7b-beta", use_flash_attention_2=True, torch_dtype=torch.bfloat16, trust_remote_code=True)

Evaluation Results

	1 - AccBio	1 - AccCyber	MMLU
Origin	0.352	0.608	0.585
NPO	0.581	0.616	0.476
SimNPO	0.584	0.678	0.471

Citation

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

@article{fan2024simplicity,
  title={Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning},
  author={Fan, Chongyu and Liu, Jiancheng and Lin, Licong and Jia, Jinghan and Zhang, Ruiqi and Mei, Song and Liu, Sijia},
  journal={arXiv preprint arXiv:2410.07163},
  year={2024}
}