huggingface/trl Releases

github.com · 2026-06-28 · by Long Nguyen ·github

Train transformer language models with reinforcement learning. - Release v1.7.0 · huggingface/trl

huggingface/trl

Features

SFT default loss_type is now "chunked_nll" The flip announced in v1.6 has landed. Setting loss_type is optional, and the default now resolves to "chunked_nll" — giving every SFTTrainer run...

source

github.com · 24 images · 214 links

Comments (0)

No comments yet