Spaces:

ggml-org
/

gguf-my-repo

Running on A10G

Errors when quanting Llama 3 based models

#62

by YorkieOH10 - opened May 12

May 12

Hey, thanks for this awesome tool. I'm facing some errors when I try and quant Llama 3 based models. For the large majority I see this error:

This GGUF file is for Little Endian only

ggml.ai org May 16

Hi @YorkieOH10 - This should be fixed on the latest. Can you try again and if it persists then send me the hub model ID for the offending repo?

May 21

Hi @reach-vb sorry for the late reply, can confirm that llama 3 based models now work. Cheers!

YorkieOH10 changed discussion status to closed May 21

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment