DPO fine-tuned Mistral 7B beats Llama 70B on MT Bench(huggingface.co)
huggingface.co
DPO fine-tuned Mistral 7B beats Llama 70B on MT Bench
https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
2 comments
Can anyone corroborate this anecdotally? I.e. has anyone actually looked at the output of the two models side-by-side for common tasks? There's lots of talks these days about academic benchmarks being pretty "broken" for modern LMs, and not really properly showcasing the differences between models. I wonder if that's the case here or if the model is genuinely better.
I dunno. I totally missed this and will check it out.
- Huggingface is less likely to "cheat" by training on tests than other orgs, I think.
- Some finetunes are really good at a particular test (like XWin). This isnt necessarily a bad thing, if they are good at a specific niche.
- Huggingface is less likely to "cheat" by training on tests than other orgs, I think.
- Some finetunes are really good at a particular test (like XWin). This isnt necessarily a bad thing, if they are good at a specific niche.
> <|system|>, <|user|> and <|model|>.
Oh hey, thats almost Metharme's format.
It must originate from an older model, as most new models dont use that syntax.
Oh hey, thats almost Metharme's format.
It must originate from an older model, as most new models dont use that syntax.