Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -3,13 +3,10 @@ license: apache-2.0
|
|
| 3 |
tags: [openpi, pi0.5, robotics, vla, piper, cube-stacking]
|
| 4 |
---
|
| 5 |
|
| 6 |
-
# pi05_piper_stacking_v3 - step
|
| 7 |
|
| 8 |
-
pi0.5 (action_horizon 50) full fine-tune of pi05_base on
|
| 9 |
-
|
| 10 |
-
(155 episodes cube stacking = v2 + ~44 correction episodes).
|
| 11 |
-
|
| 12 |
-
**Checkpoint: step 5000 / 10000** (latest pushed). Inference artifacts only (params/ + assets/norm_stats); no train_state/.
|
| 13 |
Prompt: `stack red cube on blue cube`
|
| 14 |
|
| 15 |
```python
|
|
|
|
| 3 |
tags: [openpi, pi0.5, robotics, vla, piper, cube-stacking]
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# pi05_piper_stacking_v3 - step 7500
|
| 7 |
|
| 8 |
+
pi0.5 (action_horizon 50) full fine-tune of pi05_base on axiboai/piper_stacking_v3 (155 eps = v2 + ~44 corrections).
|
| 9 |
+
Latest checkpoint pushed: **step 7500 / 10000**. Inference artifacts only (params + assets/norm_stats; no train_state).
|
|
|
|
|
|
|
|
|
|
| 10 |
Prompt: `stack red cube on blue cube`
|
| 11 |
|
| 12 |
```python
|