Video-Text-to-Text
Transformers
Safetensors
llava_onevision
image-text-to-text
multimodal
multilingual
vlm
translation
Instructions to use utter-project/TowerVideo-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use utter-project/TowerVideo-9B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("utter-project/TowerVideo-9B") model = AutoModelForImageTextToText.from_pretrained("utter-project/TowerVideo-9B") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_token": "<image>", | |
| "num_image_tokens": 729, | |
| "processor_class": "LlavaOnevisionProcessor", | |
| "video_token": "<video>", | |
| "vision_aspect_ratio": "anyres_max_9", | |
| "vision_feature_select_strategy": "full" | |
| } | |