Visual Question Answering
Transformers
Safetensors
English
videollama2_mistral
text-generation
multimodal large language model
large video-language model
Instructions to use DAMO-NLP-SG/VideoLLaMA2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA2-7B 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/VideoLLaMA2-7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA2-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.model from DAMO-NLP-SG/VideoLLaMA2-7B: direct link, hf CLI and curl.
- Browser
- Download file 493 kB
-
https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B/resolve/main/tokenizer.model
- Command line
-
hf download hf://DAMO-NLP-SG/VideoLLaMA2-7B/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B/resolve/main/tokenizer.model
493 kB
- Xet hash:
- 1e090c2d2774ea7875da72d682c12600bd69085e9c28674b917a49fe82ccffe2
- Size of remote file:
- 493 kB
- SHA256:
- dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.