panopstor/EveryDream
Text-to-Image
•
Updated
•
353
•
10
Victor Hall
panopstor
AI & ML interests
data engineering, production infrastructure, product development
Recent Activity
replied to
appliedml42's
post
about 1 month ago
I am trying to find resources that explain how I can protect against instruction following capability degradation due to LoRA fine-tuning.
For example, I fine-tuned Llama 3.2 3B Instruct on https://huggingface.co/datasets/cornell-movie-review-data/rotten_tomatoes dataset and saw significant degradation in ifeval benchmark scores.
I would appreciate any pointers 🙏🏽
Organizations
