Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,39 @@
|
|
1 |
-
---
|
2 |
-
license:
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: robotics
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- VLA
|
9 |
+
---
|
10 |
+
# Model Card for Hume-System2
|
11 |
+
|
12 |
+
|
13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
14 |
+
System 2 pretrianed weights of a Dual-System Visual-Language-Action model for accelerating training of System 2.
|
15 |
+
- Paper: [https://arxiv.org/abs/2505.21432](https://arxiv.org/abs/2505.21432)
|
16 |
+
- Homepage: [https://hume-vla.github.io](https://hume-vla.github.io)
|
17 |
+
- Codebase: [🦾 Hume: A Dual-System VLA with System2 Thinking](https://github.com/hume-vla/hume) 
|
18 |
+
|
19 |
+
|
20 |
+
## Uses
|
21 |
+
|
22 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
23 |
+
- Download the weights
|
24 |
+
- Set `pretrained_policy` to the path to weights in [scripts/train_s2.sh](https://github.com/hume-vla/hume/blob/main/scripts/train_s2.sh#L54)
|
25 |
+
- Launch training `bash scripts/train_s2.sh`
|
26 |
+
|
27 |
+
## Citation
|
28 |
+
|
29 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
30 |
+
|
31 |
+
|
32 |
+
```BibTeX
|
33 |
+
@article{song2025hume,
|
34 |
+
title={Hume: Introducing System-2 Thinking in Visual-Language-Action Model},
|
35 |
+
author={Anonimous Authors},
|
36 |
+
journal={arXiv preprint arXiv:2505.21432},
|
37 |
+
year={2025}
|
38 |
+
}
|
39 |
+
```
|