Instructions to use hf-internal-testing/tiny-random-CLIPModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/tiny-random-CLIPModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="hf-internal-testing/tiny-random-CLIPModel") 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("hf-internal-testing/tiny-random-CLIPModel") model = AutoModelForZeroShotImageClassification.from_pretrained("hf-internal-testing/tiny-random-CLIPModel") - Notebooks
- Google Colab
- Kaggle
Fix config
#4
by Xenova HF Staff - opened
from transformers import CLIPVisionModelWithProjection
m = CLIPVisionModelWithProjection.from_pretrained('hf-internal-testing/tiny-random-CLIPModel', revision='main') # FAILS
m = CLIPVisionModelWithProjection.from_pretrained('hf-internal-testing/tiny-random-CLIPModel', revision='refs/pr/4') # WORKS
Xenova changed pull request status to merged