Instructions to use OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat with Transformers:

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

pipe = pipeline("text-generation", model="OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat")
model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat"
# 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-TOFU-forget05-Llama-2-7b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat

SGLang

How to use OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat 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-TOFU-forget05-Llama-2-7b-chat" \
    --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-TOFU-forget05-Llama-2-7b-chat",
		"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-TOFU-forget05-Llama-2-7b-chat" \
        --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-TOFU-forget05-Llama-2-7b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat with Docker Model Runner:
```
docker model run hf.co/OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat
```

SimNPO-Unlearned Model on Task "TOFU - Forget05"

Model Details

Unlearning:
- Task: 🤗datasets/locuslab/TOFU - Forget05
- Method: SimNPO
Origin Model: 🤗OPTML-Group/TOFU-origin-Llama-2-7b-chat
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: 1e-5
beta: 2.5
lambda: 0.1375
gamma: 0.0

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat", use_flash_attention_2=True, torch_dtype=torch.bfloat16, trust_remote_code=True)

Evaluation Results

	Forgeting Quality (FQ)	Model Utility (MU)
Origin	0.00	0.62
Retrain	1.00	0.62
NPO	0.79	0.57
SimNPO	0.99	0.58

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}
}