Guilherme34/Samantha-qwen-vision-0.5b its a vision model based on llava, it would be great if you can quantize this...

#161
by Guilherme34 - opened

i know its not a conventional gguf quantizing method, but i think you can do it

I am honestly sorry to be of so little help to you, but this model is not directly supported by llama.cpp, and I don't know what to do to convert it, if it can be done.

mradermacher changed discussion status to closed

Sign up or log in to comment