trlX
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
trlX scores 3.9/10 (Emerging) in Fine-Tuning.
Language Python License MIT Stars 4.8k★ Type library Self-host Yes Repo CarperAI/trlx Homepage https://github.com/CarperAI/trlx
Quality
Emerging 3.9
Adoption 42
Activity 2
Maturity 65
Community 43
Capability 50
Show the math
Overall 3.9/10
value = 3.9/10
score = value
Adoption 4.8/10
value = 41.9/100
score = 1 + 9 * value / 100
Activity 1.1/10
value = 1.6/100
score = 1 + 9 * value / 100
Maturity 6.8/10
value = 64.6/100
score = 1 + 9 * value / 100
Community 4.9/10
value = 43.2/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
4.8k★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
3.8y Project age
2.5y ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Inactive
No push in 2.5y
No commits in over a year; effectively dormant.
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
rlhf ppo ilql distributed preference