raft
RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.
lumpenspace/raft
View on GitHub ↗RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.
raft grew +0.6% in the last 30 days, ranks 154th of 203 in Fine-Tuning (LoRA / PEFT), last commit 40 days ago.
Star trajectory
79 days tracked+0.6% in 30d, above the Fine-Tuning (LoRA / PEFT) median of +0.1%.
Last commit 40 days ago, fresher than the median of 259d.
How it compares in Fine-Tuning (LoRA / PEFT)
Ranked 154th of 203 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 2
- Forks
- 25
- Watchers
- 3
- Open issues
- 0
- Releases
- 8
- Created
- 2023-10-20
- Stars this week
- +1
You've seen where raft 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.