Video-Text-to-Text
Transformers
Safetensors
English
videollama2_qwen2
text-generation
large video-language model
Instructions to use DAMO-NLP-SG/VideoLLaMA2.1-7B-16F with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA2.1-7B-16F with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA2.1-7B-16F", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- abb9487c325eb83162e6038bbe66ecb4f79ab6e39fd269580d248be646bae878
- Size of remote file:
- 7.1 kB
- SHA256:
- 49e7ab23d09d19332cdb60923c3d53cb438fbccea97f38fd7ebb22d2798cb4b3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.