Article
62
Leonie Monigatti
iamleonie
AI & ML interests
None yet
Recent Activity
upvoted an article 2 days ago
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps liked a model 2 days ago
Akahsizrr/Cyber-Prime-1-2.6B reacted to sergiopaniego's post with 🔥 2 days ago
Can you do RL over taste?
I've spent some time reproducing, in the open, Surya N's idea of training a model to paint with code. It's a coding model that learns to paint watercolours by writing JS code, trained with GRPO. I used TRL and OpenEnv for this, with the whole pipeline running on Hugging Face.
The interesting part is that the reward has no correct answer, unlike a math problem. In this case it's based on the artistic preferences of the person who builds the dataset.
Everything is published: the environment, the reference pool, the trained adapters, every painting of every run with the code that made it, and a write-up with all the decisions, including the ones that went wrong.
Blog post: https://huggingface.co/blog/train-to-paint-with-codeOrganizations
datasets 0
None public yet