Commit
•
6964520
1
Parent(s):
a169d47
Update README.md
Browse files
README.md
CHANGED
@@ -3,22 +3,19 @@ license: mit
|
|
3 |
---
|
4 |
# RDT-1B
|
5 |
|
6 |
-
RDT-1B is a 1B-parameter
|
7 |
64 robot actions. RDT is inherently compatible with almost all kinds of modern mobile manipulators, from single-arm to dual-arm, joint to EEF, pos. to vel., and even with a mobile chassis.
|
8 |
|
9 |
-
|
10 |
-
-->
|
11 |
-
<!-- ### Model Description
|
12 |
|
13 |
-
|
14 |
-
- **Language(s) (NLP):** [More Information Needed]
|
15 |
-
- **License:** [More Information Needed]
|
16 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
17 |
-
-->
|
18 |
-
|
19 |
-
### Model Sources
|
20 |
|
21 |
-
|
|
|
|
|
|
|
|
|
|
|
22 |
|
23 |
- **Repository:** [More Information Needed]
|
24 |
- **Paper :** [More Information Needed]
|
@@ -26,7 +23,7 @@ RDT-1B is a 1B-parameter (largest to date) imitation learning Diffusion Transfor
|
|
26 |
|
27 |
## Uses
|
28 |
|
29 |
-
RDT-1B supports finetuning on custom dataset, deploying and inferencing on real-robots
|
30 |
|
31 |
Please refer to [our repository](https://github.com/GeneralEmbodiedSystem/RoboticsDiffusionTransformer/blob/main/docs/pretrain.md) for all the above guides.
|
32 |
|
|
|
3 |
---
|
4 |
# RDT-1B
|
5 |
|
6 |
+
RDT-1B is a 1B-parameter imitation learning Diffusion Transformer pre-trained on 1M+ multi-robot episodes. Given a language instruction and 3-view RGB image observations, RDT can predict the next
|
7 |
64 robot actions. RDT is inherently compatible with almost all kinds of modern mobile manipulators, from single-arm to dual-arm, joint to EEF, pos. to vel., and even with a mobile chassis.
|
8 |
|
9 |
+
All the code and model weights are licensed under MIT license.
|
|
|
|
|
10 |
|
11 |
+
Please refer to our [project page](), [github repository]() and [paper]() for more information.
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
+
## Model Details
|
14 |
+
|
15 |
+
- **Developed by** Thu-ml team
|
16 |
+
- **License:** MIT
|
17 |
+
- **Pretrain dataset:** [More Information Needed]
|
18 |
+
- **Finetune dataset:** [More Information Needed]
|
19 |
|
20 |
- **Repository:** [More Information Needed]
|
21 |
- **Paper :** [More Information Needed]
|
|
|
23 |
|
24 |
## Uses
|
25 |
|
26 |
+
RDT-1B supports finetuning and pre-training on custom dataset, as well as deploying and inferencing on real-robots.
|
27 |
|
28 |
Please refer to [our repository](https://github.com/GeneralEmbodiedSystem/RoboticsDiffusionTransformer/blob/main/docs/pretrain.md) for all the above guides.
|
29 |
|