TRL
Train transformer language models with reinforcement learning.
TRL scores 7.6/10 (Strong) in Fine-Tuning.
Language Python License Apache-2.0 Stars 18.8k★ Type library Self-host Yes Repo huggingface/trl Homepage https://huggingface.co/docs/trl
Quality
Strong 7.6
Adoption 57
Activity 87
Maturity 100
Community 62
Capability 50
Show the math
Overall 7.6/10
value = 7.6/10
score = value
Adoption 6.1/10
value = 56.8/100
score = 1 + 9 * value / 100
Activity 8.8/10
value = 86.7/100
score = 1 + 9 * value / 100
Maturity 10/10
value = 100/100
score = 1 + 9 * value / 100
Community 6.5/10
value = 61.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
18.8k★ GitHub stars
490/90d Recent commits
15 devs/90d Recent contributors
6.3y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
rlhf dpo grpo post-training transformers