mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-18 10:10:08 +00:00
Remove previous pi0 and rename pi0_openpi and pi05_openpi
This commit is contained in:
@@ -43,7 +43,7 @@ This diverse training mixture creates a "curriculum" that enables generalization
|
||||
|
||||
2. Apply the custom patches:
|
||||
```bash
|
||||
cp -r ./src/lerobot/policies/pi05_openpi/transformers_replace/* \
|
||||
cp -r ./src/lerobot/policies/pi05/transformers_replace/* \
|
||||
$(python -c "import transformers, os; print(os.path.dirname(transformers.__file__))")
|
||||
```
|
||||
|
||||
@@ -72,7 +72,7 @@ pip install transformers==4.53.2
|
||||
To use π₀.₅ in your LeRobot configuration, specify the policy type as:
|
||||
|
||||
```python
|
||||
policy.type=pi05_openpi
|
||||
policy.type=pi05
|
||||
```
|
||||
|
||||
## Training
|
||||
@@ -84,7 +84,7 @@ Here's a complete training command for finetuning the base π₀.₅ model on yo
|
||||
```bash
|
||||
python src/lerobot/scripts/train.py \
|
||||
--dataset.repo_id=your_dataset \
|
||||
--policy.type=pi05_openpi \
|
||||
--policy.type=pi05 \
|
||||
--output_dir=./outputs/pi0_training \
|
||||
--job_name=pi0_training \
|
||||
--policy.repo_id=pepijn223/pi05_base_fp32 \
|
||||
|
||||
Reference in New Issue
Block a user