Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

GGUF/GPTQ models for LLaVA-1.5 #526

Closed
shahizat opened this issue Oct 11, 2023 · 3 comments
Closed

GGUF/GPTQ models for LLaVA-1.5 #526

shahizat opened this issue Oct 11, 2023 · 3 comments

Comments

@shahizat
Copy link

Question

Hello,

Is anyone aware of the 4-bit quantized models for LLaVA-1.5 available on Hugging Face?

Thanks in advance!
@barshag
Copy link

barshag commented Oct 12, 2023

what are the system requirement for that? (running solely on CPU?)

@aiaicode
Copy link

https://huggingface.co/mys/ggml_llava-v1.5-7b
https://huggingface.co/mys/ggml_llava-v1.5-13b

7b works better than 13b for now.

Use the llama.cpp repo and run the make command and use ./lava

Runs on CPU. More info on this PR

@haotian-liu
Copy link
Owner

The bug seems to be fixed in ggml-org/llama.cpp#3645
Now the quality for both 7b and 13b are improved.

Closing this now.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@haotian-liu @shahizat @barshag @aiaicode