Add embodied_ma checkpoint README
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- pi0.5
|
| 5 |
+
- robotwin
|
| 6 |
+
- embodied-ma
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# embodied_ma
|
| 10 |
+
|
| 11 |
+
Finetuned pi0.5 20k checkpoints for RoboTwin tasks.
|
| 12 |
+
|
| 13 |
+
- `dump_bin_bigbin/pi05_20k_left_right_lora`: 20k-step pi0.5 LoRA/safetensors checkpoint trained on the left/right split 100-episode dataset derived from 50 official Aloha-AgileX clean demos.
|
| 14 |
+
- `handover_block/pi05_20k_left_right_lora`: 20k-step pi0.5 LoRA/safetensors checkpoint trained on the left/right split 100-episode dataset derived from 50 official Aloha-AgileX clean demos.
|
| 15 |
+
|
| 16 |
+
Each checkpoint folder includes `model.safetensors` and the corresponding `assets/.../norm_stats.json`.
|