Dexmal commited on
update README
Browse files
README.md
CHANGED
|
@@ -31,6 +31,15 @@ DM0.5 is Dexmal's next-generation Vision-Language-Action model (VLA) for open-wo
|
|
| 31 |
|
| 32 |
OpenDM provides DM0.5 model weights, training and inference scripts, dataset registration examples, and evaluation workflows for researchers and developers to train, fine-tune, evaluate, and deploy the model.
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
## Quick Start
|
| 35 |
|
| 36 |
We recommend using Docker to set up the runtime environment first, which helps avoid version mismatches across CUDA, PyTorch, flash-attn, and other dependencies on the host machine.
|
|
|
|
| 31 |
|
| 32 |
OpenDM provides DM0.5 model weights, training and inference scripts, dataset registration examples, and evaluation workflows for researchers and developers to train, fine-tune, evaluate, and deploy the model.
|
| 33 |
|
| 34 |
+
|
| 35 |
+
## Fine-Tuned Models
|
| 36 |
+
|
| 37 |
+
| Model | Description | Checkpoint | Documentation |
|
| 38 |
+
| --- | --- | --- | --- |
|
| 39 |
+
| DM05-libero | LIBERO fine-tuned DM0.5 model for evaluation | [🤗 Dexmal/DM05-libero](https://huggingface.co/Dexmal/DM05-libero) | [Training & Evaluation](https://github.com/dexmal/opendm/blob/main/docs/en/dm05_libero.md) |
|
| 40 |
+
| DM05-robotwin2 | RoboTwin2.0 fine-tuned DM0.5 model for evaluation | [🤗 Dexmal/DM05-robotwin2](https://huggingface.co/Dexmal/DM05-robotwin2) | [Training & Evaluation](https://github.com/dexmal/opendm/blob/main/docs/en/dm05_robotwin2.md) |
|
| 41 |
+
|
| 42 |
+
|
| 43 |
## Quick Start
|
| 44 |
|
| 45 |
We recommend using Docker to set up the runtime environment first, which helps avoid version mismatches across CUDA, PyTorch, flash-attn, and other dependencies on the host machine.
|