Why llama2 and not mistral 7b?

by Kernel - opened Mar 15

Discussion

Kernel

Mar 15

Can you also fine-tune mixtral 8x7b? That is gonna be mind-blowing

akanyaani

Yellow.ai org Mar 16

Hello @Kernel , we experimented with Mixtral for one of the downstream task, but unfortunately, it didn't perform as well as LLAMA2. That's why we opted for LLAMA2. However, we appreciate your suggestion and will certainly consider trying Mixtral for the next version.

louisowen6 changed discussion status to closed Mar 17

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment