Video-Text-to-Text
Transformers
Safetensors
internvl
image-text-to-text
video
dense-video-captioning
temporal-grounding
highlight-detection
video-reasoning
Instructions to use andaba/TEMPURA-InternVL3-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use andaba/TEMPURA-InternVL3-2B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("andaba/TEMPURA-InternVL3-2B") model = AutoModelForMultimodalLM.from_pretrained("andaba/TEMPURA-InternVL3-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from andaba/TEMPURA-InternVL3-2B: direct link, hf CLI and curl.
- Browser
- Download file 1.37 kB
-
https://huggingface.co/andaba/TEMPURA-InternVL3-2B/resolve/main/processor_config.json
- Command line
-
hf download hf://andaba/TEMPURA-InternVL3-2B/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/andaba/TEMPURA-InternVL3-2B/resolve/main/processor_config.json
1.37 kB
| { | |
| "image_processor": { | |
| "crop_to_patches": false, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "GotOcr2ImageProcessorFast", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "max_patches": 12, | |
| "min_patches": 1, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 448, | |
| "width": 448 | |
| } | |
| }, | |
| "image_seq_length": 256, | |
| "processor_class": "InternVLProcessor", | |
| "video_processor": { | |
| "crop_to_patches": false, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": false, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "GotOcr2ImageProcessorFast", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "initial_shift": true, | |
| "max_patches": 12, | |
| "min_patches": 1, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "height": 448, | |
| "width": 448 | |
| }, | |
| "video_processor_type": "InternVLVideoProcessor" | |
| } | |
| } | |