News for hackers. Stuff that matters.

A comment on Show HN: How we got fine-tuning Mistral-7B to not suck. Parent comment

Re:Show HN: How we got fine-tuning Mistral-7B to not suck by gbickford on Thursday February 08, 2024 @02:20AM (#39299262)
Have you tried generating two sets of qapairs, one with bad answers, and using DPO?
[ Parent | on HN ]
Re:Show HN: How we got fine-tuning Mistral-7B to not suck by lewq on Thursday February 08, 2024 @10:32AM (#39303084)
Not yet, sounds promising!
[ Parent | on HN ]