Robotics
LeRobot
Safetensors
pi05

Pi05 policy for Task 1 MM (500 episodes)

This Pi05 policy was fine-tuned from lerobot/pi05_libero with LeRobot on cbrian/merge_task1_MM_epi_500. See train_config.json for the complete training configuration.

The repository includes the policy weights plus the preprocessing and postprocessing artifacts needed by LeRobot.

Downloads last month
4
Safetensors
Model size
4B params
Tensor type
F32
·
BF16
·
Video Preview
loading

Dataset used to train jaywu109/pi05_task1_MM3_epi_500_step_25000_batch_32