Duplicated from Mantis-VL/mantis-8b-idefics2-video-eval-anno-real_4096_regression
How to use TIGER-Lab/VideoScore with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="TIGER-Lab/VideoScore")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSequenceClassification processor = AutoProcessor.from_pretrained("TIGER-Lab/VideoScore") model = AutoModelForSequenceClassification.from_pretrained("TIGER-Lab/VideoScore", device_map="auto")
https://huggingface.co/TIGER-Lab/VideoScore/resolve/main/processor_config.json
hf download hf://TIGER-Lab/VideoScore/processor_config.json
curl -L -o processor_config.json https://huggingface.co/TIGER-Lab/VideoScore/resolve/main/processor_config.json
