How to use reneepr/clip-action-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="reneepr/clip-action-model") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForImageClassification processor = AutoProcessor.from_pretrained("reneepr/clip-action-model") model = AutoModelForImageClassification.from_pretrained("reneepr/clip-action-model", device_map="auto")
https://huggingface.co/reneepr/clip-action-model/resolve/main/tokenizer.json
hf download hf://reneepr/clip-action-model/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/reneepr/clip-action-model/resolve/main/tokenizer.json
