Instructions to use mlpc-lab/BLIVA_Vicuna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlpc-lab/BLIVA_Vicuna with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="mlpc-lab/BLIVA_Vicuna")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mlpc-lab/BLIVA_Vicuna", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Missing config.json
The model can't be used for now. Getting the following stacktrace:
venv/lib/python3.9/site-packages/transformers/utils/hub.py in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)
478 if revision is None:
479 revision = "main"
--> 480 raise EnvironmentError(
481 f"{path_or_repo_id} does not appear to have a file named {full_filename}. Checkout "
482 f"'https://huggingface.co/{path_or_repo_id}/{revision}' for available files."
OSError: mlpc-lab/BLIVA_Vicuna does not appear to have a file named config.json. Checkout 'https://huggingface.co/mlpc-lab/BLIVA_Vicuna/main' for available files.
We are now supporting to download this weight locally. Then following our GitHub repo (https://github.com/mlpc-ucsd/BLIVA) to put your weight path.