Video-Text-to-Text
Transformers
Safetensors
llava_onevision
image-text-to-text
multimodal
multilingual
vlm
translation
Instructions to use utter-project/TowerVideo-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use utter-project/TowerVideo-2B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("utter-project/TowerVideo-2B") model = AutoModelForImageTextToText.from_pretrained("utter-project/TowerVideo-2B") - Notebooks
- Google Colab
- Kaggle
| { | |
| "do_convert_rgb": false, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_grid_pinpoints": [ | |
| [ | |
| 384, | |
| 384 | |
| ], | |
| [ | |
| 384, | |
| 768 | |
| ], | |
| [ | |
| 384, | |
| 1152 | |
| ], | |
| [ | |
| 384, | |
| 1536 | |
| ], | |
| [ | |
| 384, | |
| 1920 | |
| ], | |
| [ | |
| 384, | |
| 2304 | |
| ], | |
| [ | |
| 768, | |
| 384 | |
| ], | |
| [ | |
| 768, | |
| 768 | |
| ], | |
| [ | |
| 768, | |
| 1152 | |
| ], | |
| [ | |
| 768, | |
| 1536 | |
| ], | |
| [ | |
| 768, | |
| 1920 | |
| ], | |
| [ | |
| 768, | |
| 2304 | |
| ], | |
| [ | |
| 1152, | |
| 384 | |
| ], | |
| [ | |
| 1152, | |
| 768 | |
| ], | |
| [ | |
| 1152, | |
| 1152 | |
| ], | |
| [ | |
| 1152, | |
| 1536 | |
| ], | |
| [ | |
| 1152, | |
| 1920 | |
| ], | |
| [ | |
| 1152, | |
| 2304 | |
| ], | |
| [ | |
| 1536, | |
| 384 | |
| ], | |
| [ | |
| 1536, | |
| 768 | |
| ], | |
| [ | |
| 1536, | |
| 1152 | |
| ], | |
| [ | |
| 1536, | |
| 1536 | |
| ], | |
| [ | |
| 1536, | |
| 1920 | |
| ], | |
| [ | |
| 1536, | |
| 2304 | |
| ], | |
| [ | |
| 1920, | |
| 384 | |
| ], | |
| [ | |
| 1920, | |
| 768 | |
| ], | |
| [ | |
| 1920, | |
| 1152 | |
| ], | |
| [ | |
| 1920, | |
| 1536 | |
| ], | |
| [ | |
| 1920, | |
| 1920 | |
| ], | |
| [ | |
| 1920, | |
| 2304 | |
| ], | |
| [ | |
| 2304, | |
| 384 | |
| ], | |
| [ | |
| 2304, | |
| 768 | |
| ], | |
| [ | |
| 2304, | |
| 1152 | |
| ], | |
| [ | |
| 2304, | |
| 1536 | |
| ], | |
| [ | |
| 2304, | |
| 1920 | |
| ], | |
| [ | |
| 2304, | |
| 2304 | |
| ] | |
| ], | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "LlavaOnevisionImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "LlavaOnevisionProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 384, | |
| "width": 384 | |
| }, | |
| "vision_feature_select_strategy": "full" | |
| } | |