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.

语言：Python · GitHub 星标：177 · Fork：25

话题：embedding · fine · llm · rag

在 GitHub 上查看原仓库