pypi.org : mod-trl
Train transformer language models with reinforcement learning.
Registry
-
Source
- Documentation
- JSON
purl: pkg:pypi/mod-trl
Keywords:
transformers
, huggingface
, language modeling
, post-training
, rlhf
, sft
, dpo
, grpo
License: Apache-2.0
Latest release: 2 months ago
First release: 2 months ago
Downloads: 9 last month
Stars: 15,353 on GitHub
Forks: 2,163 on GitHub
See more repository details: repos.ecosyste.ms
Last synced: 2 days ago
Loading...
Readme
Loading...