Commit
•
8aa386c
1
Parent(s):
7fd572e
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ tags:
|
|
| 15 |
---
|
| 16 |
# RDT-170M
|
| 17 |
|
| 18 |
-
RDT-170M is a 170M-parameter imitation learning Diffusion Transformer
|
| 19 |
64 robot actions. RDT is compatible with almost all modern mobile manipulators, from single-arm to dual-arm, joint to EEF, position to velocity, and even wheeled locomotion.
|
| 20 |
|
| 21 |
All the [code](https://github.com/thu-ml/RoboticsDiffusionTransformer/tree/main?tab=readme-ov-file), pre-trained model weights, and [data](https://huggingface.co/datasets/robotics-diffusion-transformer/rdt-ft-data) are licensed under the MIT license.
|
|
|
|
| 15 |
---
|
| 16 |
# RDT-170M
|
| 17 |
|
| 18 |
+
RDT-170M is a 170M-parameter imitation learning Diffusion Transformer **(RDT(small) in ablation)**. It has a hidden size of `1024` and a depth of `14`, which are half of that in RDT-1B. Given language instruction and RGB images of up to three views, RDT can predict the next
|
| 19 |
64 robot actions. RDT is compatible with almost all modern mobile manipulators, from single-arm to dual-arm, joint to EEF, position to velocity, and even wheeled locomotion.
|
| 20 |
|
| 21 |
All the [code](https://github.com/thu-ml/RoboticsDiffusionTransformer/tree/main?tab=readme-ov-file), pre-trained model weights, and [data](https://huggingface.co/datasets/robotics-diffusion-transformer/rdt-ft-data) are licensed under the MIT license.
|