Instructions to use laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K') tokenizer = open_clip.get_tokenizer('hf-hub:laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K') - Notebooks
- Google Colab
- Kaggle
Deploying as a Space throws a runtime error
#2
by tdingman-scale - opened
Tried to deploy my own version and got this:
===== Application Startup at 2023-05-05 16:57:46 =====
/home/user/.pyenv/versions/3.8.9/lib/python3.8/site-packages/gradio/interface.py:94: UserWarning: gr.Interface.load() will be deprecated. Use gr.load() instead.
warnings.warn("gr.Interface.load() will be deprecated. Use gr.load() instead.")
Fetching model from: https://huggingface.co/laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K
Traceback (most recent call last):
File "app.py", line 3, in <module>
gr.Interface.load("models/laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K").launch()
File "/home/user/.pyenv/versions/3.8.9/lib/python3.8/site-packages/gradio/interface.py", line 95, in load
return external.load(
File "/home/user/.pyenv/versions/3.8.9/lib/python3.8/site-packages/gradio/external.py", line 68, in load
return load_blocks_from_repo(
File "/home/user/.pyenv/versions/3.8.9/lib/python3.8/site-packages/gradio/external.py", line 107, in load_blocks_from_repo
blocks: gradio.Blocks = factory_methods[src](name, api_key, alias, **kwargs)
File "/home/user/.pyenv/versions/3.8.9/lib/python3.8/site-packages/gradio/external.py", line 383, in from_model
raise ValueError(f"Unsupported pipeline type: {p}")
ValueError: Unsupported pipeline type: zero-shot-image-classification