News for hackers. Stuff that matters.

A comment on Intel Neural-Chat-7B Model Achieves Top Ranking on LLM Leaderboard. Parent comment

Re:Intel Neural-Chat-7B Model Achieves Top Ranking on LLM Le... by hskalin on Sunday December 03, 2023 @10:36AM (#38507797)
That is what my experience has been. I have tried OpenHermes2.5 (very hyped 7B model) vs basic Mistral 7B and tbh I prefer Mistral's answer for most things.
[ Parent | on HN ]
Re:Intel Neural-Chat-7B Model Achieves Top Ranking on LLM Le... by dmezzetti on Sunday December 03, 2023 @10:38AM (#38507823)
Exactly, benchmarks are just a guide. Same thing with vector models. Likely just a matter of how much your data overlaps with the fine-tuning dataset for a particular model.
[ Parent | on HN ]