Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 💪 RIPT-VLA: Reinforcement Interactive Post-Training for Vision-Language-Action Models
|
| 2 |
|
| 3 |
**Authors**: Shuhan Tan, Kairan Dou, Yue Zhao, Philipp Krähenbühl
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- yifengzhu-hf/LIBERO-datasets
|
| 4 |
+
base_model:
|
| 5 |
+
- moojink/openvla-7b-oft-finetuned-libero-spatial
|
| 6 |
+
- moojink/openvla-7b-oft-finetuned-libero-10
|
| 7 |
+
- moojink/openvla-7b-oft-finetuned-libero-object
|
| 8 |
+
- moojink/openvla-7b-oft-finetuned-libero-goal
|
| 9 |
+
---
|
| 10 |
# 💪 RIPT-VLA: Reinforcement Interactive Post-Training for Vision-Language-Action Models
|
| 11 |
|
| 12 |
**Authors**: Shuhan Tan, Kairan Dou, Yue Zhao, Philipp Krähenbühl
|