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

Libraries

How to use OPTML-Group/TOFU-origin-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/TOFU-origin-Llama-2-7b-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OPTML-Group/TOFU-origin-Llama-2-7b-chat")
model = AutoModelForCausalLM.from_pretrained("OPTML-Group/TOFU-origin-Llama-2-7b-chat", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

TOFU-origin-Llama-2-7b-chat / README.md

ljcc

Update README.md

1c8bd8a verified almost 2 years ago

preview code

Raw

History Blame

1.76 kB

	---
	license: mit
	datasets:
	- locuslab/TOFU
	language:
	- en
	base_model:
	- NousResearch/Llama-2-7b-chat-hf
	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
	---

	# Origin Model on Task "TOFU"

	## Model Details
	- Training:
	- Task: [🤗datasets/locuslab/TOFU](https://huggingface.co/datasets/locuslab/TOFU)
	- Method: Fine tune
	- Base Model: [🤗NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf)
	- Code Base: [github.com/OPTML-Group/Unlearn-Simple](https://github.com/OPTML-Group/Unlearn-Simple)
	- Research Paper:
	- ["Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"](https://arxiv.org/abs/2410.07163)
	- ["TOFU: A Task of Fictitious Unlearning for LLMs"](https://arxiv.org/abs/2401.06121)


	## Loading the Model

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

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

	## 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}
	}
	```

	## Reporting Issues

	Reporting issues with the model: [github.com/OPTML-Group/Unlearn-Simple](https://github.com/OPTML-Group/Unlearn-Simple)