Instructions to use ModalityDance/Omni-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModalityDance/Omni-R1 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ModalityDance/Omni-R1") model = AutoModelForMultimodalLM.from_pretrained("ModalityDance/Omni-R1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from ModalityDance/Omni-R1: direct link, hf CLI and curl.
- Browser
- Download file 102 Bytes
-
https://huggingface.co/ModalityDance/Omni-R1/resolve/main/processor_config.json
- Command line
-
hf download hf://ModalityDance/Omni-R1/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/ModalityDance/Omni-R1/resolve/main/processor_config.json
102 Bytes
| { | |
| "image_seq_length": 1024, | |
| "image_token": "<image>", | |
| "processor_class": "ChameleonProcessor" | |
| } | |