Re:Learnings from fine-tuning LLM on my Telegram messages
by skerit on Monday November 27, 2023 @03:34PM
(#38437864)
I've used vast.ai to do some fine-tuning just a few days ago. It is indeed pretty great, though some servers fail to start up properly, or have some weird performance issues. I also wish they had more templates to try.
[ Parent
| on HN ]
Re:Learnings from fine-tuning LLM on my Telegram messages
by icelancer on Monday November 27, 2023 @07:46PM
(#38440793)
Yeah it works pretty well for the price - just need to be comfortable with running code and putting data on random peoples' computers (which I am for certain things). Someone on HN posted a script or snippet of output on mass-testing vast.ai servers for connectivity and configuration, and auto-labeling them using their API. Wish I could find it now... maybe with the search?