Q6/Q8 GGUF ?

#1
by ivanpzk - opened

Hi,
Thank you for this great model. I'd be interested by a Q6 or Q8 GGUF version, is it planned ? Thanks

Sure, I'll add them... btw, can you show how to use gguf with hf or other frameworks so that I can add it to readme?

Thanks

Added

Thanks for your answer. Personnaly i use gguf exclusively with llama cpp python, i'm a novice so i didn't try other framework like ollama or vllm. I launch models with the llama class, and use appropriate prompt template.
https://github.com/abetlen/llama-cpp-python
PS : I'm a fan of your posts on medium, i work when i'm not on cloud mission on a neo4j app in my company, thanks for sharing helpful and interesting content :)

Sign up or log in to comment