Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
SFT
Video-Understanding
Image-Understanding
MOSS-VL
OpenMOSS
multimodal
video
vision-language
custom_code
Instructions to use OpenMOSS-Team/MOSS-VL-Instruct-0708 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Instruct-0708 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Instruct-0708", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
possible to have quantized version
#2
by jar67 - opened
Many others and I have 16GB Vram. A quantized version would be great.
I have tried Moss-Audio understanding model...so amazing!
Thanks for the feedback!
We plan to release a quantized MOSS-VL version that runs within 24GB VRAM first. We’re also aware that many users have 16GB GPUs, and we’ll continue optimizing and validating support for 16GB VRAM in a future release.