dgrachev/pi05_subtask_base

pi05_subtask base checkpoint

A derived copy of lerobot/pi05_base prepared for the lerobot_policy_pi05_subtask LeRobot plugin (π0.5 with System-1 subtask generation, following openpi_subtask).

The model weights are bit-identical to lerobot/pi05_base. Only two metadata files differ:

• config.json: policy type is pi05_subtask instead of pi05.

• policy_preprocessor.json: pi05's pi05_prepare_state_tokenizer_processor_step + tokenizer_processor steps are replaced by pi05_subtask_tokenize_processor_step, which builds the two-segment prompt

  context (no loss):   "Task: {task}.; State: {256-bin ints}; Subtask: "
  predicted (CE loss): "{subtask}.;\nAction: " + EOS
  

  and emits a subtask region mask alongside the language tokens.

This exists because LeRobot instantiates processor pipelines from the checkpoint's policy_preprocessor.json (by processor-step registry name), so fine-tuning the subtask policy directly from lerobot/pi05_base would silently install plain pi05's tokenizer steps.

Usage

Requires the lerobot_policy_pi05_subtask plugin installed (LeRobot auto-imports lerobot_policy_* distributions). In a training config:

"policy": {
    "type": "pi05_subtask",
    "pretrained_path": "dgrachev/pi05_subtask_base",
    ...
}

During training the subtask string is read from complementary_data["subtask"] when the dataset provides one, and falls back to the task string otherwise.

Regenerate with scripts/prepare_base_checkpoint.py from the plugin repository.