---
license: cc
---


This model provides an initialization checkpoint for training DM0 VLA Model


| Model                 | Description                                                                 | Input Images                                  | Action Dim | Model Size |
| -                     | -                                                                           | -                                             |-           | -          |
| DM0-Base | DM0 base vision-language action model                   | Triple Views                                   | 32         | 2.4B         |