visualwebarena icon indicating copy to clipboard operation
visualwebarena copied to clipboard

Published 20 hours ago • verified publisher icon web-arena-x

Reproducing open-source model results

Open anithselva opened this issue 9 months ago • 2 comments

Hello,

I'm looking to reproduce some of the open-source model results from the VWA paper: (1) Mixtral-8x7B model as the LLM backbone for Caption-augmented model (2) CogVLM for the Multimodal Model.

Could someone share with me any flags/commands or instructions to setup these configurations for eval?

anithselva avatar Apr 29 '24 15:04 anithselva