Post
1307
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 cornell-movie-review-data/rotten_tomatoes dataset and saw significant degradation in ifeval benchmark scores.
I would appreciate any pointers 🙏🏽
For example, I fine-tuned Llama 3.2 3B Instruct on cornell-movie-review-data/rotten_tomatoes dataset and saw significant degradation in ifeval benchmark scores.
I would appreciate any pointers 🙏🏽