News for hackers. Stuff that matters.

A comment on Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4. Parent comment

Re:Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4 by llwj on Tuesday September 12, 2023 @06:10PM (#37489262)
I see wrong responses about 1% of the time, but I love it, considering parsing raw text output without function calling had a much higher error rate.
[ Parent | on HN ]

There are no comments on this comment yet.