rameyjm7
/

llm-preference-unlearning

large-language-models

preference-modeling

Model card Files Files and versions

llm-preference-unlearning / .gitignore

rameyjm7's picture

more testing with A-LoRA and inception/movie files

3de3bed 5 months ago

history blame contribute delete

92 Bytes

	lpu-env/
	activations/
	gradients/
	logs/
	saliency/
	*.csv
	*.json
	fisher/
	unlearned_checkpoint/