LlamaIndex Webinar: Retrieval-Augmented Fine-Tuning (RAFT)

RAFT - Retrieval Augmented Fine Tuning 🔥

​Retrieval-Augmented Fine-Tuning (RAFT) is a new technique to fine-tune pre-trained LLMs for specific domain RAG settings.

​Conventional RAG is like an open-book exam, retrieving documents from an index to provide context for answering queries. This makes it more effective than the closed-book exam setting where LLMs rely solely on their pre-training and fine-tuning to respond to prompts, but doesn't allow the LLM to learn the domain beforehand.

​In this webinar we feature Tianjun Zhang and Shishir Patil, the two lead co-authors of RAFT. They present an overview of RAFT and also engage in a discussion on fine-tuning and RAG.

​RAFT blog: https://gorilla.cs.berkeley.edu/blogs...

*Extra*

​Thanks to Ravi, you can now generate a dataset for RAFT using our RAFTDatasetPack: https://llamahub.ai/l/llama-packs/lla...

​Notebook: https://github.com/run-llama/llama_in...

Timeline:
00:00-26:48 RAFT Presentation
26:48-28:50 Short LlamaIndex + RAFT Demo
28:50 Q&A