Video-Text-to-Text
Transformers
Safetensors
English
molmo2
image-text-to-text
multimodal
olmo
molmo
custom_code
Instructions to use allenai/Molmo2-VideoPoint-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use allenai/Molmo2-VideoPoint-4B with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("allenai/Molmo2-VideoPoint-4B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_molmo2.Molmo2Processor" | |
| }, | |
| "image_use_col_tokens": true, | |
| "processor_class": "Molmo2Processor", | |
| "use_frame_special_tokens": false, | |
| "use_single_crop_col_tokens": false, | |
| "use_single_crop_start_token": true, | |
| "video_use_col_tokens": false | |
| } | |