docs: license metadata reflects the Gemma Terms of Use
Browse files
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
| 3 |
pipeline_tag: robotics
|
| 4 |
tags: [robotics, vla, openpi, manipulation, maniguard, franka]
|
| 5 |
---
|
|
@@ -28,3 +30,12 @@ A ManiGuard fine-tuned VLA checkpoint (openpi).
|
|
| 28 |
url = {https://arxiv.org/abs/2608.17386},
|
| 29 |
}
|
| 30 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: gemma-terms-of-use
|
| 4 |
+
license_link: https://ai.google.dev/gemma/terms
|
| 5 |
pipeline_tag: robotics
|
| 6 |
tags: [robotics, vla, openpi, manipulation, maniguard, franka]
|
| 7 |
---
|
|
|
|
| 30 |
url = {https://arxiv.org/abs/2608.17386},
|
| 31 |
}
|
| 32 |
```
|
| 33 |
+
|
| 34 |
+
## License
|
| 35 |
+
|
| 36 |
+
The fine-tuned weights derive from a Physical Intelligence openpi base model whose
|
| 37 |
+
VLM backbone is PaliGemma; use of these weights is therefore subject to the
|
| 38 |
+
[Gemma Terms of Use](https://ai.google.dev/gemma/terms) (including the
|
| 39 |
+
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy)),
|
| 40 |
+
which downstream users must pass on. The openpi training code and ManiGuard's own
|
| 41 |
+
contributions are Apache-2.0.
|