Skip to content
Robotics

ACT для SO-101

политика достаёт кубик из ящика

2 min read

Это ACT-политика имитационного обучения от fabono: предсказывает короткие чанки действий, а не отдельные шаги. Обучена в LeRobot для робота so_follower с камерами wrist и top; на входе 6-мерное состояние и два изображения 480×640, на выходе 6-мерное действие. Около 50M параметров.

Ключевые особенности

  • ACT учится на телеоперационных данных и, по описанию метода, часто даёт высокий success rate.
  • Две камеры: wrist и top; наблюдения — state (6,), images (3, 480, 640).
  • Задача: «Take the black cube out of the blue drawer with the yellow handle and put it on the table.»
  • Обучение: 50 эпизодов, 33 631 кадр, 30 FPS; 50 000 шагов, batch 16, AdamW, lr 1e-5.
  • Запуск и дообучение через CLI LeRobot; лицензия Apache-2.0.

Пример

lerobot-rollout \
  --strategy.type=base \
  --robot.type=so_follower \
  --robot.port=/dev/ttyACM0 \
  --robot.cameras="{ wrist: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}, top: {type: opencv, index_or_path: 2, width: 640, height: 480, fps: 30}}" \
  --policy.path=fabono/act_so101_pickup_in_drawer \
  --task="Take the black cube out of the blue drawer with the yellow handle and put it on the table." \
  --duration=60
ПодробнееБенчмарков и оценки на реальном роботе в карточке пока нет.
Данные: 50 эпизодов, 33 631 кадр, 30 FPS.
Обучение: 50k шагов, batch 16, lr 1e-5, LeRobot 0.6.1.
Лицензия Apache-2.0; требования к VRAM не указаны.
Discuss Telegram 0 27

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.

    # fabono/act_so101_pickup_in_drawer
    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 fabono/act_so101_pickup_in_drawer --local-dir ~/models/act_so101_pickup_in_drawer
    # 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 act_so101_pickup_in_drawer (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

fabono/act_so101_pickup_in_drawer
Author
fabono
Category
Robotics
Released
Posted

On NeyroLearn

Hugging Face

270

Ask AI about this model

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

Comments