Introducing DBRX: A New State-of-the-Art Open LLM by Databricks

Re:Introducing DBRX: A New State-of-the-Art Open LLM by Data... by blueblimp on Wednesday March 27, 2024 @06:17PM (#39845271)

Qwen1.5-72B-Chat is dominant in the Chatbot Arena leaderboard, though. (Miqu isn't on there due to being bootleg, but Qwen outranks Mistral Medium.)

[ Parent | on HN ]

Re:Introducing DBRX: A New State-of-the-Art Open LLM by Data... by brucethemoose2 on Thursday March 28, 2024 @01:47PM (#39855004)

Yeah I know, hence its odd I found it kind of dumb for personal use. Moreso with the smaller models, which lost an objective benchmark I have to some Mistral finetunes.

And I don't think I was using it wrong. I know, for instance, the Chinese language models are funny about sampling since I run Yi all the time.

[ Parent | on HN ]