How do I access my models I saved inside a folder?

Beginners
1

I have fine tuned a model and saved it on my hugging-face inside a particular folder since I will save multiple folders having trained models for my use-case. I am able to access the path & print its contents using:

fs = HfFileSystem(token=hf_read)
file_find = fs.ls(folder_path, detail=True)

But how do I access the files for:
model, tokenizer = FastLanguageModel.from_pretrained(model_name=model_name,…)

Although I have used repo_type=space (also tried saving & using from Model), my error:
HFValidationError( huggingface_hub.errors.HFValidationError: Repo id must be in the form ‘repo_name’ or ‘namespace/repo_name’: ‘//<folder_path>’. Use repo_type argument if needed.

Some variations I tried I got:
Error loading model: <folder_path>/*.json (invalid repository id)

2 Likes
2

The functions related to HF models are designed on the premise that there is one model per repo, so they may not work properly.
In the case of Diffusers, you may be able to use the subfolder option to get around this.