Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
multimodal
text-generation-inference
Instructions to use OpenGVLab/VideoChat-R1_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/VideoChat-R1_7B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("OpenGVLab/VideoChat-R1_7B") model = AutoModelForImageTextToText.from_pretrained("OpenGVLab/VideoChat-R1_7B") - Notebooks
- Google Colab
- Kaggle
How many devices are needed for the GRPO tuning as your paper mentioned?
#1
by JasonLee996 - opened
As title.
4 or 8 A100-80G :), even less might be fine
4 or 8 A100-80G :), even less might be fine
Thx alot
JasonLee996 changed discussion status to closed