News for hackers. Stuff that matters.
Re:Ask HN: How do I train a custom LLM/ChatGPT on my own doc... by thorum on Monday December 25, 2023 @03:00PM (#38765604)
Has anyone tried using an LLM for the retrieval stage? Instead of using vector embeddings, have a (small, fast) LLM literally scan the entire corpus in chunks extracting relevant sections?
Re:Ask HN: How do I train a custom LLM/ChatGPT on my own doc... by spullara on Monday December 25, 2023 @03:02PM (#38765638)
That would still be very slow with any reasonably large corpus.