Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: lerobot
|
4 |
+
pipeline_tag: robotics
|
5 |
+
---
|
6 |
+
π0+FAST: Efficient Action Tokenization for Vision-Language-Action Models
|
7 |
+
|
8 |
+
[Paper](https://arxiv.org/abs/2501.09747)
|
9 |
+
[Jax code](https://github.com/Physical-Intelligence/openpi)
|
10 |
+
|
11 |
+
Designed by Physical Intelligence. Ported from Jax by Hugging Face.
|
12 |
+
|
13 |
+
Example of finetuning the pi0+FAST pretrained model (`pi0_fast_base` in `openpi`):
|
14 |
+
```bash
|
15 |
+
python lerobot/scripts/train.py \
|
16 |
+
--policy.path=lerobot/pi0fast_base \
|
17 |
+
--dataset.repo_id=danaaubakirova/koch_test
|
18 |
+
```
|
19 |
+
|
20 |
+
Example of training the pi0+FAST neural network with from scratch:
|
21 |
+
```bash
|
22 |
+
python lerobot/scripts/train.py \
|
23 |
+
--policy.type=pi0fast \
|
24 |
+
--dataset.repo_id=danaaubakirova/koch_test
|
25 |
+
```
|
26 |
+
|
27 |
+
Example of using the pi0 pretrained model outside LeRobot training framework:
|
28 |
+
```python
|
29 |
+
policy = PI0FASTPolicy.from_pretrained("lerobot/pi0fast_base")
|