How to use DAMO-NLP-SG/VideoLLaMA2-72B 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="DAMO-NLP-SG/VideoLLaMA2-72B")
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA2-72B", device_map="auto")
https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B/resolve/main/vocab.json
hf download hf://DAMO-NLP-SG/VideoLLaMA2-72B/vocab.json
curl -L -o vocab.json https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B/resolve/main/vocab.json
