zlacker

[parent] [thread] 1 comments
1. loudma+(OP)[view] [source] 2023-09-12 19:57:49
The Huggingface Leaderboard is mostly dominated by Llama 2 variants: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderb...

It depends a lot on what you're trying to do. If have a focused use case of the type of fine-tuning you want, you can probably get away with one of the smaller models.

Another thing to look out for is Retrieval Augmented Generation (RAG). I don't see it in wide use yet, but it may turn out to more useful than fine tuning for a lot of situations.

replies(1): >>0x008+zlw
2. 0x008+zlw[view] [source] 2023-09-22 13:08:36
>>loudma+(OP)
RAG is THE rage right now. Everybody is talking about it in enterprise world because they want to make all their legacy documents searchable.
[go to top]