Spaces:
Running
on
CPU Upgrade
Error Converting PEFT Fine-Tuned CodeLlama-7B to GGUF: Gated Repo Access Issue
I have finetuned "meta-llama/CodeLlama-7b-hf" using peft lora, when i try to convert it into gguf format, I have granted access of this gated repo already,
I get this error "
ā ERROR
Error converting to GGUF F16: b'INFO:lora-to-gguf:Loading base model from Hugging Face: meta-llama/CodeLlama-7b-hf\nERROR:lora-to-gguf:Failed to load base model config: You are trying to access a gated repo.\nMake sure to have access to it at https://huggingface.co/meta-llama/CodeLlama-7b-hf.\n403 Client Error. (Request ID: Root=1-67ceb578-05a2d96328788566370b119b;2f99b6f0-ddbb-43dd-b0bf-7b130b154b16)\n\nCannot access gated repo for url https://huggingface.co/meta-llama/CodeLlama-7b-hf/resolve/main/config.json.\nAccess to model meta-llama/CodeLlama-7b-hf is restricted and you are not in the authorized list. Visit https://huggingface.co/meta-llama/CodeLlama-7b-hf to ask for access.\nERROR:lora-to-gguf:Please try downloading the base model and add its path to --base\n'"
Sam issue here> I used AutoTrain to do some refinement in Bielik 4.5B and 1.5B, got the files but can't convert it neither using llama.cpp nor this tool here.