Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
agentscope-ai/Trinity-RFT
View on GitHub ↗Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Trinity-RFT grew +1.0% in the last 30 days, ranks 90th of 203 in Fine-Tuning (LoRA / PEFT), last commit 16 days ago.
Star trajectory
125 days tracked2026-06-21710 stars today2026-10-25
Momentum
+1.0% in 30d, above the Fine-Tuning (LoRA / PEFT) median of +0.1%.
Maintenance
Last commit 16 days ago, fresher than the median of 259d.
How it compares in Fine-Tuning (LoRA / PEFT)
Trinity-RFT
710
stars
+1.0% 30d
commit 16 days ago
Fine-Tuning (LoRA / PEFT) median
533
stars
+0.1% 30d
commit ~259d ago
Leader · LLMs-from-scratch
107.2k
stars
+1.6% 30d
commit 22 days ago
Ranked 90th of 203 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 29
- Forks
- 87
- Watchers
- 6
- Open issues
- 43
- Releases
- 14
- Created
- 2025-04-09
- Stars this week
- +0
You've seen where Trinity-RFT stands today.
Get the moves before everyone else: the 5 Fine-Tuning (LoRA / PEFT) repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.