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:
# pip install -U transformers accelerate # 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
Download model-00002-of-00004.safetensors from OpenMOSS-Team/MOSS-VL-Realtime-FP8: direct link, hf CLI and curl.
- Browser
- Download file 4.97 GB
-
https://huggingface.co/OpenMOSS-Team/MOSS-VL-Realtime-FP8/resolve/main/model-00002-of-00004.safetensors
- Command line
-
hf download hf://OpenMOSS-Team/MOSS-VL-Realtime-FP8/model-00002-of-00004.safetensors
-
curl -L -o model-00002-of-00004.safetensors https://huggingface.co/OpenMOSS-Team/MOSS-VL-Realtime-FP8/resolve/main/model-00002-of-00004.safetensors
4.97 GB
- Xet hash:
- 5389a2c8b2401d5bdfe60f8674a970b8985c4558e0fff3e904f91da8c641e3f7
- Size of remote file:
- 4.97 GB
- SHA256:
- 17467922bd278d495c0716005f61f7d6f1d7e952603a78fa76ab7be9eca04421
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.