thomasgauthier/autojev-27b-GGUF
26B • Updated • 149 • 1
Thomas Gauthier-Caron
thomasgauthier
AI & ML interests
None yet
Recent Activity
new activity about 23 hours ago
denis-pplx/autojev-27b:Thank You So Much! | GGUF Compatibility? updated a model about 24 hours ago
thomasgauthier/autojev-27b-GGUF published a model 1 day ago
thomasgauthier/autojev-27b-GGUFOrganizations
Thank You So Much! | GGUF Compatibility?
2
#1 opened 1 day ago
by 
mfielding92
updated a
model about 24 hours ago
published a
model 1 day ago
liked a
model 1 day ago
liked 3
models 2 days ago
reacted to sergiopaniego's post with 🔥 4 days ago
Post
2121
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-code
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-code
liked a
model 4 days ago
liked a
Space 7 days ago
liked 2
models 7 days ago
liked 2
models 11 days ago
liked a
model 15 days ago
liked 2
models 29 days ago
upvoted a paper about 1 month ago
liked a
model about 1 month ago
upvoted a collection about 1 month ago