Robotics
Transformers
Safetensors
English
molmoact
image-text-to-text
molmo
olmo
reasoning
vla
manipulation
custom_code
Instructions to use allenai/MolmoAct-7B-O-0812 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use allenai/MolmoAct-7B-O-0812 with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("allenai/MolmoAct-7B-O-0812", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_molmoact.MolmoActImageProcessor", | |
| "AutoProcessor": "processing_molmoact.MolmoActProcessor" | |
| }, | |
| "base_image_input_size": [ | |
| 336, | |
| 336 | |
| ], | |
| "crop_mode": "overlap-and-resize-c2", | |
| "do_convert_rgb": true, | |
| "do_pad": true, | |
| "image_patch_size": 14, | |
| "image_pooling_h": 2, | |
| "image_pooling_w": 2, | |
| "image_processor_type": "MolmoActImageProcessor", | |
| "max_crops": 8, | |
| "max_multi_image_crops": 8, | |
| "normalize_mode": "openai", | |
| "overlap_margins": [ | |
| 4, | |
| 4 | |
| ], | |
| "pad_value": 0.0, | |
| "processor_class": "MolmoActProcessor", | |
| "resize_mode": "default" | |
| } | |