avnlp/rag-model-training
Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.
GitHub repository with 8 stars and 2 forks.
Language: Python
Topics: adaptive-rag, agentic-rag, crag, grpo, llm-training, rag, rezero, rq-rag, self-rag, sft