How to use microsoft/xclip-base-patch16-hmdb-4-shot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="microsoft/xclip-base-patch16-hmdb-4-shot")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("microsoft/xclip-base-patch16-hmdb-4-shot") model = AutoModel.from_pretrained("microsoft/xclip-base-patch16-hmdb-4-shot", device_map="auto")
https://huggingface.co/microsoft/xclip-base-patch16-hmdb-4-shot/resolve/main/tokenizer.json
hf download hf://microsoft/xclip-base-patch16-hmdb-4-shot/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/microsoft/xclip-base-patch16-hmdb-4-shot/resolve/main/tokenizer.json
