Myungkyu/pi0_5_robodojo_preset_b64_60k

pi05robodojopresetb64_60k

Low-level policy for RoboDojo long-horizon (8 real-robot bimanual tabletop tasks, 100 demonstrations each), fine-tuned from lerobot/pi05_base on `Myungkyu/RoboDojo-preset-gemini` — demonstrations with dense subtask labels from the subtask preset.

• —Architecture: Pi0.5 vanilla (three live camera views, no keyframe slot, no memory attestation)
• —Optimizer batch 64, 60000 steps, final checkpoint
• —Inputs: head + left/right wrist images, proprioception, the current subtask text (no keyframe input)

Configs reference the base backbone / tokenizer by hub id or by the training site's local path — point them at your local copies before loading.