Instructions to use zer0int/LongCLIP-GmP-ViT-L-14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zer0int/LongCLIP-GmP-ViT-L-14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="zer0int/LongCLIP-GmP-ViT-L-14") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("zer0int/LongCLIP-GmP-ViT-L-14") model = AutoModelForZeroShotImageClassification.from_pretrained("zer0int/LongCLIP-GmP-ViT-L-14") - Notebooks
- Google Colab
- Kaggle
Update config.json to include "max_position_embeddings"
#7
by Heasterian - opened
It makes easier to use model as it will load without defining this variable it in code.
Thank you for this very useful contribution! ❤️
zer0int changed pull request status to merged