Re:The Coming of Local LLMs
by causi on Tuesday April 11, 2023 @03:02PM
(#35529785)
The way OpenAI has set their models up for prompting and follow-up is where their real advantage is. It's very hard to take a model you can run locally and just go "Hey, write me a powershell script to convert all these files into this format. Split them up so they're no more than an hour each. Ok, change it to also denoise them."
[ Parent
| on HN ]
Re:The Coming of Local LLMs
by thewataccount on Tuesday April 11, 2023 @03:20PM
(#35530027)
Are you talking about the RLHF? That's where Vicuna/Alpaca and other finetuning help a lot.
There's also already tools for conversation flows (which just means you prepend the conversation history to the prompt).
I'm not saying the performance is nearly as good, but the actual workflow does already exist and is massively improving. The interesting part to me is that this finetuning can be done in a couple few hours on a consumer gpu (4090).