I was trying to fine tune llama2 for specific usecase.In that after fine tuning when I'm trying load fine tune model locally I'm getting error below mentioned

Note: The fine-tuned model is locally saved.

Notebook link

OSError: llama-2-7b-mlabonne-enhanced does not appear to have a file named config.json. Checkout ‘https://huggingface.co/llama-2-7b-mlabonne-enhanced/None’ for available files.

when finetuning a model… depending on the code it saves the adapter version of it… you have to merge the adapter with the original model.

idk how you trained it, but for Lora is called merge_adapters()