Instructions to use StrongRoboticsLab/pi05-so100-diverse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use StrongRoboticsLab/pi05-so100-diverse with LeRobot:
- Notebooks
- Google Colab
- Kaggle
bot commited on
Commit ·
fc597b1
1
Parent(s): d390ed0
Re-enable gradient checkpointing (OOM without it), batch 32
Browse files- train_cloud.sh +1 -1
train_cloud.sh
CHANGED
|
@@ -35,7 +35,7 @@ python3.12 -m accelerate.commands.launch $ACCEL_FLAGS \
|
|
| 35 |
--policy.path=lerobot/pi05_base \
|
| 36 |
--policy.train_expert_only=true \
|
| 37 |
--policy.dtype=bfloat16 \
|
| 38 |
-
--policy.gradient_checkpointing=
|
| 39 |
--policy.push_to_hub=true \
|
| 40 |
--policy.repo_id=StrongRoboticsLab/pi05-so100-diverse \
|
| 41 |
--policy.normalization_mapping='{"VISUAL": "IDENTITY", "STATE": "MEAN_STD", "ACTION": "MEAN_STD"}' \
|
|
|
|
| 35 |
--policy.path=lerobot/pi05_base \
|
| 36 |
--policy.train_expert_only=true \
|
| 37 |
--policy.dtype=bfloat16 \
|
| 38 |
+
--policy.gradient_checkpointing=true \
|
| 39 |
--policy.push_to_hub=true \
|
| 40 |
--policy.repo_id=StrongRoboticsLab/pi05-so100-diverse \
|
| 41 |
--policy.normalization_mapping='{"VISUAL": "IDENTITY", "STATE": "MEAN_STD", "ACTION": "MEAN_STD"}' \
|