search

unslothai / unsloth

Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory
https://unsloth.ai
Apache License 2.0
18k stars 1.25k forks source link

Uploading gguf model to huggingface after trainning #764

Open myrulezzz opened 4 months ago

myrulezzz commented 4 months ago

Hi something is wrong. I finetunned a model in google colab and when trying to upload q4 to huggingface i get this error RuntimeError: Unsloth: The file 'llama.cpp/llama-quantize' or 'llama.cpp/quantize' does not exist. But we expect this file to exist! Maybe the llama.cpp developers changed the name?

danielhanchen commented 3 months ago

Could you try again - hopefully it works now

okoliechykwuka commented 3 months ago

The issue persists.

sourceful-tolu commented 3 months ago

I'm also getting this error. See screenshot

image

Any solution to this?

sourceful-tolu commented 3 months ago

Just tried again, with no changes and it appears this has been fixed

danielhanchen commented 3 months ago

Apologies llama.cpp can sometimes be a pain :( If you're on a local machine, best to delete the entire llama.cpp folder, and re use Unsloth again, so we can pull the latest llama.cpp folder