Transformers
unlearning
alignment
large-language-models
qwen2.5
lora
fine-tuning
safety
preference-modeling
Instructions to use rameyjm7/llm-preference-unlearning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rameyjm7/llm-preference-unlearning with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rameyjm7/llm-preference-unlearning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download notebooks/05_fisher_information.ipynb from rameyjm7/llm-preference-unlearning: direct link, hf CLI and curl.
- Browser
- Download file 214 kB
-
https://huggingface.co/rameyjm7/llm-preference-unlearning/resolve/main/notebooks/05_fisher_information.ipynb
- Command line
-
hf download hf://rameyjm7/llm-preference-unlearning/notebooks/05_fisher_information.ipynb
-
curl -L -o 05_fisher_information.ipynb https://huggingface.co/rameyjm7/llm-preference-unlearning/resolve/main/notebooks/05_fisher_information.ipynb
214 kB