Hugging Face's logo

Spaces:
ggml-org
/
gguf-my-repo
Running on A10G

App Files Community
136

inconsistent quantization for authenticated repos? out of space or rate limit?

#109
by 5fp - opened
Discussion
5fp
•
edited Aug 4

I did this for Q4_0 and Q4_K_M
, the third time for the Q6_K shows:

Error: [Errno 2] No such file or directory: 'Meta-Llama-3.1-8B/original/consolidated.00.pth'

I made sure to logout, login and refresh page

Clausss
•
edited Aug 4

I have same error I gguf 8 bit llama 3.1 8b them I want 4 bit and same problem that dont have pth file(I can 4 bit if space restart by schedule)

reach-vb
 ggml.ai org

Closing this as it's an error for a base model, which doesn't make much sense to quantize in the first place.

reach-vb changed discussion status to closed

Sign up or log in to comment