LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
LLaMA-Factory scores 7.7/10 (Strong) in Fine-Tuning.
Language Python License Apache-2.0 Stars 72.9k★ Type heavyweight Self-host Yes Repo hiyouga/LLaMA-Factory Homepage https://llamafactory.readthedocs.io
Quality
Strong 7.7
Adoption 72
Activity 75
Maturity 97
Community 74
Capability 50
Show the math
Overall 7.7/10
value = 7.7/10
score = value
Adoption 7.4/10
value = 71.6/100
score = 1 + 9 * value / 100
Activity 7.7/10
value = 74.7/100
score = 1 + 9 * value / 100
Maturity 9.7/10
value = 96.5/100
score = 1 + 9 * value / 100
Community 7.7/10
value = 74.2/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
72.9k★ GitHub stars
67/90d Recent commits
33 devs/90d Recent contributors
3.1y 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).
fine-tuning webui lora rlhf peft