News for hackers. Stuff that matters.
Re:New models and developer products announced at OpenAI DevDay by muttled on Monday November 06, 2023 @04:43PM (#38169443)
For me personally, being able to fine-tune the local LLM's at a much higher rank and training more layers is very useful for (somewhat unreliably) embedding information. AFAIK the OpenAI fine-tuning is more geared towards formatting the output.
Re:New models and developer products announced at OpenAI DevDay by bigfudge on Monday November 06, 2023 @05:06PM (#38169738)
As I understand it, fine tuning is never really about adding content. RAG and related techniques are likely cheaper/better if that’s what you want.
Re:New models and developer products announced at OpenAI DevDay by antupis on Tuesday November 07, 2023 @02:15AM (#38174073)
yup how I understand fine tuning is more about adding context and bigger picture. RAG is more about adding actual content. Good system probably needs both in long run.