Skip to content
Robotics

model_act_test_gazeuse_resnet_15K_18_11

a LeRobot robotic arm policy

2 min readupdated

This model uses the ACT algorithm (Action Chunking with Transformers, an imitation learning method that predicts short sequences of actions rather than single steps) to control an so_follower robotic arm. The policy takes joint states and feeds from three cameras (front, side, and top) as input, outputting control actions. Trained on teleoperation demonstrations, it handles picking up a yellow marker and placing it into a pink box. It is built for researchers and practitioners working on home and lab robotics with the LeRobot framework.

Key features

  • Supports three cameras (front, side, top) at 480x640 resolution
  • Predicts 6-step control action sequences (action chunking)
  • Compatible with the so_follower robot hardware configuration
  • Trained on network demonstrations recorded at 30 FPS

What you can do

  • Deploy the pre-trained policy on a physical so_follower robot for object sorting tasks
  • Integrate the model into your own imitation learning experiments within the LeRobot ecosystem
  • Test policy inference using LeRobot command-line tools

Example

lerobot-rollout \
  --strategy.type=base \
  --robot.type=so_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=Tridex/model_act_test_gazeuse_resnet_15K_18_11 \
  --task="take the yellow fluo and drop it inside the pink box" \
  --duration=60
Read moreDetails
License: apache-2.0
Dataset: 10 episodes, 4584 frames
Training parameters: 15000 steps, batch size 8, adamw optimizer, learning rate 1e-05
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.

    # Tridex/model_act_test_gazeuse_resnet_15K_18_11
    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 Tridex/model_act_test_gazeuse_resnet_15K_18_11 --local-dir ~/models/model_act_test_gazeuse_resnet_15K_18_11
    # 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 model_act_test_gazeuse_resnet_15K_18_11 (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

Tridex/model_act_test_gazeuse_resnet_15K_18_11
Author
Tridex
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