diff --git a/docs/source/pi0.mdx b/docs/source/pi0.mdx index 315c642e6..31d6356fb 100644 --- a/docs/source/pi0.mdx +++ b/docs/source/pi0.mdx @@ -101,8 +101,11 @@ python src/lerobot/scripts/train.py \ - **`--policy.compile_model=true`**: Enables model compilation for faster training - **`--policy.gradient_checkpointing=true`**: Reduces memory usage significantly during training - **`--policy.dtype=bfloat16`**: Use mixed precision training for efficiency -- **`--policy.pretrained_path=pepijn223/pi0_base_fp32`**: The base π₀.₅ model to finetune, options are: `pepijn223/pi0_base_fp32`, `pepijn223/pi0_libero_fp32`, `pepijn223/pi0_droid_fp32` - **`--batch_size=32`**: Batch size for training, adapt this based on your GPU memory +- **`--policy.pretrained_path=pepijn223/pi0_base_fp32`**: The base π₀ model you want to finetune, options are: + - \*\* [pepijn223/pi0_base_fp32](https://huggingface.co/pepijn223/pi0_base_fp32) + - \*\* [pepijn223/pi0_libero_fp32](https://huggingface.co/pepijn223/pi0_libero_fp32) (specifically trained on the Libero dataset) + - \*\* [pepijn223/pi0_droid_fp32](https://huggingface.co/pepijn223/pi0_droid_fp32) (specifically trained on the Droid dataset) ## License diff --git a/docs/source/pi05.mdx b/docs/source/pi05.mdx index 49d06da26..11e941258 100644 --- a/docs/source/pi05.mdx +++ b/docs/source/pi05.mdx @@ -104,8 +104,11 @@ python src/lerobot/scripts/train.py \ - **`--policy.compile_model=true`**: Enables model compilation for faster training - **`--policy.gradient_checkpointing=true`**: Reduces memory usage significantly during training - **`--policy.dtype=bfloat16`**: Use mixed precision training for efficiency -- **`--policy.pretrained_path=pepijn223/pi05_base_fp32`**: The base π₀.₅ model to finetune, options are: `pepijn223/pi05_base_fp32`, `pepijn223/pi05_libero_fp32`, `pepijn223/pi05_droid_fp32` - **`--batch_size=32`**: Batch size for training, adapt this based on your GPU memory +- **`--policy.pretrained_path=pepijn223/pi05_base_fp32`**: The base π₀.₅ model you want to finetune, options are: + - \*\* [pepijn223/pi05_base_fp32](https://huggingface.co/pepijn223/pi05_base_fp32) + - \*\* [pepijn223/pi05_libero_fp32](https://huggingface.co/pepijn223/pi05_libero_fp32) (specifically trained on the Libero dataset) + - \*\* [pepijn223/pi05_droid_fp32](https://huggingface.co/pepijn223/pi05_droid_fp32) (specifically trained on the Droid dataset) ## Performance Results