Skip to content
Robotics

pi0 (SO101)

VLA-политика для захвата апельсина

1 min read

Это дообученная версия general-purpose VLA-модели π₀ (pi0) от Physical Intelligence, адаптированная в LeRobot. Политика управляет роботом so101_follower по двум камерам — front и wrist — и выполняет задачу «Grab orange and place into plate». В метаданных указано 4,03 млрд параметров.

Ключевые особенности

  • Входы: observation.state (6,), изображения front и wrist 480×640; выход — action (6,).
  • Обучена на датасете LightwheelAI/leisaac-pick-orange: 60 эпизодов, 36 293 кадра, 30 FPS.
  • Робот so101_follower; камеры front и wrist.
  • 15 000 шагов обучения, batch size 32, AdamW, learning rate 0.0001, seed 1000, LeRobot 0.6.2.

Пример

Фрагмент запуска политики на роботе:

lerobot-rollout \
  --strategy.type=base \
  --robot.type=so101_follower \
  --robot.port=<your_robot_port> \
  --robot.cameras='{ front: {type: opencv, index_or_path: <index>, width: 640, height: 480, fps: 30}, wrist: {type: opencv, index_or_path: <index>, width: 640, height: 480, fps: 30}}' \
  --policy.path=your_repo_id \
  --task='Grab orange and place into plate' \
  --duration=60

Замените порт, индексы камер и путь к политике; имена камер должны совпадать с ключами наблюдений.

ПодробнееБенчмарков нет: в карточке указано «No evaluation results».
VRAM и требования к железу не указаны.
Обучение: 15 000 шагов, batch 32, AdamW, LR 0.0001, seed 1000, LeRobot 0.6.2; лицензия gemma.
Данные: 60 эпизодов, 36 293 кадра, 30 FPS; задача — Grab orange and place into plate.
Discuss Telegram 0 36

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.

    # ImemKK/your_repo_id
    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 ImemKK/your_repo_id --local-dir ~/models/your_repo_id
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to your_repo_id
  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 your_repo_id (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

ImemKK/your_repo_id
Author
ImemKK
Category
Robotics
Released
Posted

On NeyroLearn

Hugging Face

360

Ask AI about this model

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

Comments

Robotics

gaze_act

gaze_act