Hugging Face's logo
Abhishek Patnia's picture
1

Abhishek Patnia PRO

appliedml42
shimmyshimmer's profile picture
·

AI & ML interests

SMOL LLMs, PEFT, GPU Optimization, Natural Language Processing, Trust & Safety

Recent Activity

updated a collection 5 days ago
Learn: LLM Architecture 2025
updated a collection 5 days ago
Learn: Vision Language Models
upvoted a paper 14 days ago
From Vocal Instructions to Household Tasks: The Inria Tiago++ in the euROBIN Service Robots Coopetition
View all activity

Organizations

None yet

appliedml42's activity

updated 2 collections 5 days ago
upvoted a paper 14 days ago
posted an update about 1 month ago
view post
Post
1313
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 🙏🏽
  • 1 reply
·