lumpenspace/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.

175
Stars
23
Forks
41.4
Radar Score
Stable
Momentum

Scoring Breakdown

Impact40.8
Velocity30.1
Health58.3

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python

Why it ranks

Modest but positive momentum.

RAG ยท rag frameworkTop 58% globally
View on GitHub