slime
slime is an LLM post-training framework for RL Scaling.
slime scores 6.8/10 (Solid) in Fine-Tuning.
Language Python License Apache-2.0 Stars 7.3k★ Type heavyweight Self-host Yes Repo THUDM/slime Homepage https://github.com/THUDM/slime
Quality
Solid 6.8
Adoption 47
Activity 80
Maturity 82
Community 51
Capability 50
Show the math
Overall 6.8/10
value = 6.8/10
score = value
Adoption 5.2/10
value = 46.5/100
score = 1 + 9 * value / 100
Activity 8.2/10
value = 80.4/100
score = 1 + 9 * value / 100
Maturity 8.3/10
value = 81.6/100
score = 1 + 9 * value / 100
Community 5.6/10
value = 50.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
7.3k★ GitHub stars
174/90d Recent commits
22 devs/90d Recent contributors
1y 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.
- Heavyweight
Heavyweight
Resource-heavy to run (GPU, large memory, or multi-service stack).
rl post-training megatron sglang scaling