Request gguf
#1
by
ayishfeng
- opened
Hey, can you convert Qwen2-VL-7B-Instruct-GPTQ to gguf(q8,q6,q4)
It works here, but I didn't succeed https://huggingface.co/spaces/ggml-org/gguf-my-repo
there is no lama.cpp support for Qwen2-VL....maybe soon there is a issue open on github
It would make more sense to make exl2 version because exllama now supports qwen vl