Instructions to use hqfang/molmoact2-origami with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hqfang/molmoact2-origami with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("hqfang/molmoact2-origami", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download assets/sample_wrist_right.png from hqfang/molmoact2-origami: direct link, hf CLI and curl.
- Browser
- Download file 299 kB
-
https://huggingface.co/hqfang/molmoact2-origami/resolve/main/assets/sample_wrist_right.png
- Command line
-
hf download hf://hqfang/molmoact2-origami/assets/sample_wrist_right.png
-
curl -L -o sample_wrist_right.png https://huggingface.co/hqfang/molmoact2-origami/resolve/main/assets/sample_wrist_right.png
299 kB

- Xet hash:
- 226563e2e7d04b69185b02596fb90fccc9ec76762e81d7189268c7f14fbeccf3
- Size of remote file:
- 299 kB
- SHA256:
- 174aa8d1235121558fe62a5ebba3df3e3d06cb0c1568304463f0e0c0c4ca079b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.