Improve model card: Add pipeline tag, library, and additional information (#1)
Browse files- Improve model card: Add pipeline tag, library, and additional information (7698b92b4c9321b3335b67859f25128dd707b27c)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
@@ -3,6 +3,8 @@ license: mit
|
|
3 |
tags:
|
4 |
- model_hub_mixin
|
5 |
- pytorch_model_hub_mixin
|
|
|
|
|
6 |
---
|
7 |
|
8 |
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
@@ -33,3 +35,37 @@ env_action = MinecraftWrapper.agent_action_to_env(agent_action)
|
|
33 |
# agent_action = {'buttons': tensor([1], device='cuda:0'), 'camera': tensor([54], device='cuda:0')}
|
34 |
# env_action = {'attack': array(0), 'back': array(0), 'forward': array(0), 'jump': array(0), 'left': array(0), 'right': array(0), 'sneak': array(0), 'sprint': array(0), 'use': array(0), 'drop': array(0), 'inventory': array(0), 'hotbar.1': array(0), 'hotbar.2': array(0), 'hotbar.3': array(0), 'hotbar.4': array(0), 'hotbar.5': array(0), 'hotbar.6': array(0), 'hotbar.7': array(0), 'hotbar.8': array(0), 'hotbar.9': array(0), 'camera': array([-0.61539427, 10. ])}
|
35 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
tags:
|
4 |
- model_hub_mixin
|
5 |
- pytorch_model_hub_mixin
|
6 |
+
pipeline_tag: robotics
|
7 |
+
library_name: pytorch
|
8 |
---
|
9 |
|
10 |
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
|
|
35 |
# agent_action = {'buttons': tensor([1], device='cuda:0'), 'camera': tensor([54], device='cuda:0')}
|
36 |
# env_action = {'attack': array(0), 'back': array(0), 'forward': array(0), 'jump': array(0), 'left': array(0), 'right': array(0), 'sneak': array(0), 'sprint': array(0), 'use': array(0), 'drop': array(0), 'inventory': array(0), 'hotbar.1': array(0), 'hotbar.2': array(0), 'hotbar.3': array(0), 'hotbar.4': array(0), 'hotbar.5': array(0), 'hotbar.6': array(0), 'hotbar.7': array(0), 'hotbar.8': array(0), 'hotbar.9': array(0), 'camera': array([-0.61539427, 10. ])}
|
37 |
```
|
38 |
+
|
39 |
+
## Interaction Details
|
40 |
+
|
41 |
+
Here are some interaction types:
|
42 |
+
| interaction | obj_id | function |
|
43 |
+
| --- | --- | --- |
|
44 |
+
| Hunt | 0 | Approach the animals then kill it. |
|
45 |
+
| Mine | 2 | Approach and mine the target object. |
|
46 |
+
| Interact | 3 | Approach and right click the target object. |
|
47 |
+
| Craft | 4 | Move the cursor to the item and click on it. |
|
48 |
+
| Switch | 5 | Highlight an item in the hotkey bar, then switch to holding state. |
|
49 |
+
| Approach | 6 | Approach the target object. |
|
50 |
+
|
51 |
+
## Play ROCKET-1 with Gradio
|
52 |
+
Click the following picture to learn how to play ROCKET-1 with gradio.
|
53 |
+
[](https://www.youtube.com/embed/qXLWw81p-Y0)
|
54 |
+
|
55 |
+
```sh
|
56 |
+
cd rocket/arm
|
57 |
+
python eval_rocket.py --port 8110 --sam-path "/path/to/sam2-ckpt-directory"
|
58 |
+
```
|
59 |
+
|
60 |
+
|
61 |
+
## Citing ROCKET-1
|
62 |
+
If you use ROCKET-1 in your research, please use the following BibTeX entry.
|
63 |
+
|
64 |
+
```
|
65 |
+
@article{cai2024rocket,
|
66 |
+
title={ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting},
|
67 |
+
author={Cai, Shaofei and Wang, Zihao and Lian, Kewei and Mu, Zhancun and Ma, Xiaojian and Liu, Anji and Liang, Yitao},
|
68 |
+
journal={arXiv preprint arXiv:2410.17856},
|
69 |
+
year={2024}
|
70 |
+
}
|
71 |
+
```
|