Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

We're testing different models depending on the business case. Our initial tests using 3, 7, and 8B models are working fine. We're not using the big ones since our use cases don't demand them.


Like Qwen, or Tulu3, or what?


Testing LLama, DeepSeek, and Mistral atm.


Awesome, thanks!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: