Skip to content
Robotics

openarm_insertbattery_lerobot_real_pi05_v02

VLA-политика для вставки батареи

1 min read

Это fine-tune Vision-Language-Action модели π₀.₅ (Pi05) от Physical Intelligence, адаптированный под робота openarm_umeow и опубликованный автором ethanCSL. Модель на 4,14 млрд параметров учится на реальных демонстрациях выполнять задачу: левой рукой взять зарядную станцию, правой — вставить в неё батарею.

Ключевые особенности

  • Базируется на lerobot/pi05_base; реализация для LeRobot.
  • На входе — три RGB-камеры 224×224 и состояние размерности 32.
  • На выходе — вектор действия размерности 16.
  • Обучение: 6000 шагов, batch size 32, AdamW, learning rate 2.5e-05, seed 1000, LeRobot 0.6.2.
  • Датасет: 55 эпизодов, 41 360 кадров при 30 FPS; лицензия Apache-2.0.

Пример запуска

lerobot-rollout \
  --strategy.type=base \
  --robot.type=openarm_umeow \
  --robot.port=<your_robot_port> \
  --policy.path=ethanCSL/openarm_insertbattery_lerobot_real_pi05_v02 \
  --task="Pick up the charging station with the left arm, and insert battery in it with the right arm" \
  --duration=60
ПодробнееБенчмарков нет: в карточке указано «No evaluation results».
Для запуска нужны три камеры и состояние; имена камер должны совпадать с observation keys политики.
Данные и обучение заточены под openarm_umeow; это не универсальная модель для любого робота.
Лицензия Apache-2.0, базовый чекпойнт — lerobot/pi05_base.
Discuss Telegram 0 21

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # ethanCSL/openarm_insertbattery_lerobot_real_pi05_v02
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download ethanCSL/openarm_insertbattery_lerobot_real_pi05_v02 --local-dir ~/models/openarm_insertbattery_lerobot_real_pi05_v02
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of openarm_insertbattery_lerobot_real_pi05_v02 (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

ethanCSL/openarm_insertbattery_lerobot_real_pi05_v02
Author
ethanCSL
Category
Robotics
Released
Posted

On NeyroLearn

Hugging Face

210

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments