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
Is it possible to show this model few shot examples for event tagging?
#3
by oayk - opened
Hello OpenMOSS team.
You made a great model first of all thanks for it. We are testing it on event tagging on the video like event A happening between 2.0 second and 3.5 second but sometimes model misses it. Is it possible to show it example video event for let the model recognize or understanding the events dynamics? For example can I add system prompt a video sequence that describes what I want?