How to use OpenGVLab/VideoChat-R1_7B_caption with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("OpenGVLab/VideoChat-R1_7B_caption") model = AutoModelForMultimodalLM.from_pretrained("OpenGVLab/VideoChat-R1_7B_caption", device_map="auto")
https://huggingface.co/OpenGVLab/VideoChat-R1_7B_caption/resolve/main/latest
hf download hf://OpenGVLab/VideoChat-R1_7B_caption/latest
curl -L -o latest https://huggingface.co/OpenGVLab/VideoChat-R1_7B_caption/resolve/main/latest
