Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
MOSS-VL
realtime
streaming
video-understanding
FP8
compressed-tensors
HQQ
quantized
custom_code
Instructions to use OpenMOSS-Team/MOSS-VL-Realtime-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Realtime-FP8 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Realtime-FP8", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 2c3da6082bf0250da816ed55264a9049c903eb6d793629ae371b5932f7514822
- Size of remote file:
- 11.4 MB
- SHA256:
- e7bbd0f9784004df51aca562befc3c7a8f294b4045aa8685536c35804c9aa493
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.