Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on DPO fine-tuned Mistral 7B beats Llama 70B on MT Bench. Parent comment
- 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.
There are no comments on this comment yet.
- 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.