How to use facebook/vjepa2-vith-fpc64-256 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="facebook/vjepa2-vith-fpc64-256")
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/vjepa2-vith-fpc64-256") model = AutoModel.from_pretrained("facebook/vjepa2-vith-fpc64-256", device_map="auto")
nielsr