Repository Issues

CarperAI/trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Stars
 (4,184 stars)
Forks
 (450 forks)
Indexed issues
 (2 indexed issues)
open beginner issues
 (2 open beginner issues)
Latest indexed
Jul 5, 2026
Last GitHub push
Jan 8, 2024
Contributing guide
Contributing guide
Code of conduct
Code of conduct
Dominant language
Python
PR merge metrics
 (No merged PRs in 30d)
Beginner labels
good first issue

Issues

2 open indexed issues

Open
Collapse reference+learner hydra heads when using LoRa
contributions welcomefeature requestgood first issue

CarperAI/trlx #320 opened Feb 21, 2023 · Python · 4,184 stars

Why recommendedNo assignee yet · Has a beginner-friendly label
No assignee yetHas a beginner-friendly labelContributing guide available
6 comments2 reactions0 assignees