gradient-ai/AutoYOLO

Run locally

Opened this issue · 0 comments

When running in a conda environment with CUDA set up (torch.cuda.is_available() == True), running setup.sh and then python AutoYOLO.py has many issues

  • firstly it expects tensorboard, which is not installed with the requirements file
  • the script gives this warning message:
groundingdino/models/GroundingDINO/ms_deform_attn.py:31: UserWarning: Failed to load custom C++ ops. Running on CPU mode Only!
  • The script ends with the following error:
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './datasets/dolly-v2-12b/dolly-v2-12b/'. Use `repo_type` argument if needed.

During handling of the above exception, another exception occurred:

OSError: Can't load the configuration of './datasets/dolly-v2-12b/dolly-v2-12b/'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './datasets/dolly-v2-12b/dolly-v2-12b/' is the correct path to a directory containing a config.json file

Please consider providing further steps for those running locally and I appreciate your help in solving the above problems.