Eval Request - Qwen2.5(VL) 72B

#400
by TPH441 - opened

https://huggingface.co/Qwen/Qwen2.5-72B-Instruct
https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct

I'm curious as to how text only performance differs between a model and its vision variant.

DontPlanToEnd changed discussion status to closed

Sign up or log in to comment