Instructions to use facebook/metaclip-2-worldwide-b16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/metaclip-2-worldwide-b16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="facebook/metaclip-2-worldwide-b16") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("facebook/metaclip-2-worldwide-b16") model = AutoModelForZeroShotImageClassification.from_pretrained("facebook/metaclip-2-worldwide-b16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from facebook/metaclip-2-worldwide-b16: direct link, hf CLI and curl.
- Browser
- Download file 61.3 MB
-
https://huggingface.co/facebook/metaclip-2-worldwide-b16/resolve/main/tokenizer.json
- Command line
-
hf download hf://facebook/metaclip-2-worldwide-b16/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/facebook/metaclip-2-worldwide-b16/resolve/main/tokenizer.json
61.3 MB
- Xet hash:
- 08617ca7a328f7c1473b800d3f3ec2f0a7390a93b7cc8386120a40bd84dc81c0
- Size of remote file:
- 61.3 MB
- SHA256:
- f9b777521f1113c9a64cdbd2bccbc890c17d7b4d451777cd67839cd45760da83
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.