Skip to content
Robotics

cut_act_thesis_cam3_omly

robotics policy for precision manipulation

1 min readupdated

This is a ready-to-use robotics policy trained with ACT (Action Chunking with Transformers, an imitation learning method that predicts short action sequences instead of single steps). Built for cutting tasks on a robotic arm with a specific camera setup and joint-state configuration, it was trained with the LeRobot library on teleoperation demonstrations. It is well suited for researchers and developers working in home or lab robotics.

Key features

  • Robot type: compatible with the so101_follower robotic arm.
  • Cameras: uses feeds from two cameras (wrist and side).
  • Architecture: built on Action Chunking with Transformers (ACT).
  • Dataset: trained on 103 episodes (72,725 frames at 30 FPS).

What you can do

  • Run the pre-trained policy on your robot via the LeRobot CLI utility.
  • Use the task demonstration dataset to fine-tune your own models.
  • Tune inference parameters to automate object manipulation.

Example

lerobot-rollout \
  --strategy.type=base \
  --robot.type=so101_follower \
  --robot.port= \
  --robot.cameras="{ : {type: opencv, index_or_path: , width: 640, height: 480, fps: 30}, : {type: opencv, index_or_path: , width: 640, height: 480, fps: 30}}" \
  --policy.path=Kimura-881014/cut_act_thesis_cam3_omly \
  --task="cut entangle chips" \
  --duration=60
Read moreDetails
Training steps: 20,000
Batch size: 8
Optimizer: adamw (Learning rate: 1e-05)
LeRobot version: 0.7.1
Discuss Telegram 0 23

Will it run?

Runs in F32

Fits without quantisation.

  • F32weights 0.2 GB · ready files0.7 GB
  • BF16weights 0.1 GB0.6 GB
  • FP8 / INT8recommendedweights 0.0 GB0.6 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · F32 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

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.

    # Kimura-881014/cut_act_thesis_cam3_omly
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    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 Kimura-881014/cut_act_thesis_cam3_omly --local-dir ~/models/cut_act_thesis_cam3_omly
    # 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 cut_act_thesis_cam3_omly (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

Kimura-881014/cut_act_thesis_cam3_omly
Author
Kimura-881014
Category
Robotics
Released
Posted

On NeyroLearn

Hugging Face

230

Ask AI about this model

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

Comments