ViCLIP-L-14-BVD-V-50M-s50M-b32K-WiSE-FT

import torch
import torch.nn.functional as F
from transformers import AutoModel, AutoTokenizer, AutoVideoProcessor

model = AutoModel.from_pretrained("laion/ViCLIP-L-14-BVD-V-50M-s50M-b32K-WiSE-FT", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("laion/ViCLIP-L-14-BVD-V-50M-s50M-b32K-WiSE-FT", trust_remote_code=True)
video_processor = AutoVideoProcessor.from_pretrained("laion/ViCLIP-L-14-BVD-V-50M-s50M-b32K-WiSE-FT", trust_remote_code=True)

video = video_processor("path/to/video.mp4")

labels = ["a person playing basketball", "a person swimming", "a person running"]
text_tokens = tokenizer(labels, padding="max_length", truncation=True, max_length=77, return_tensors="pt")

with torch.no_grad():
    v_feat = model.get_video_features(video["pixel_values_videos"])
    t_feat = model.get_text_features(text_tokens["input_ids"])

logits = 100.0 * v_feat @ t_feat.t()
probs = logits.softmax(dim=-1)
print("Label probs:", probs)

@misc{laionbvd2026,
      title={LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training}, 
      author={Andreas Hochlehnert and Marianna Nezhurina and Mehdi Cherti and Andrej Radonjic and Thaddäus Wiedemer and Christoph Schuhmann and Romain Beaumont and Wieland Brendel and Bernhard Schölkopf and A. Sophia Koepke and Jenia Jitsev and Matthias Bethge},
      year={2026},
      eprint={2608.24845},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.24845}, 
}