jstm/molmoact2_single_arm

Model Card for molmoact2

MolmoAct2 is an open robotics foundation model from the Allen Institute for AI (Ai2) that maps camera images and language instructions to robot action chunks. The LeRobot implementation supports training and evaluation of the regular MolmoAct2 model.

This policy has been trained and pushed to the Hub using LeRobot.

Learn how to train and run it in the LeRobot molmoact2 guide, or browse the full documentation.

---

Model Details

• License: apache-2.0
• Robot type: picksodafromcabinet
• Cameras: external1_camera, external2_camera, hand_camera

Inputs & Outputs

The policy consumes these observation features and produces these action features.

Inputs

Feature	Type	Shape
observation.state	STATE	(9,)
observation.images.external1_camera	VISUAL	(3, 480, 640)
observation.images.external2_camera	VISUAL	(3, 480, 640)
observation.images.hand_camera	VISUAL	(3, 480, 640)

Outputs

Feature	Type	Shape
action	ACTION	(7,)

Training Dataset

• Repository: pythonsong/colosseum-single-arm-jan27
• Episodes: 1539
• Frames: 350072
• Frame rate: 30 FPS
• Task(s): "Cook the item in the pan", "Hammer the nail into the surface", "Open the cabinet door", "Open the drawer", "Pick up the dish from the rack", "Pick up the soda can from the cabinet", "Place the book on the shelf", "Place the cube in the drawer", "Place the dish in the rack", "Raise the cube up from the table", "Rotate the arrow", "Scoop the banana", "Stack one cube on top of another", "Lift the peg upright", "Plug in the charger", "Insert the peg from the side"

Training Configuration

Setting	Value
Training steps	10000
Batch size	32
Optimizer	adamw
Learning rate	1e-05
Seed	1000
LeRobot version	0.6.0

---

How to Get Started with the Model

New to LeRobot? These guides cover the full workflow:

• Install LeRobot — set up the lerobot package.
• Hardware setup — assemble, wire, and calibrate your robot and cameras.
• Record data & train a policy — the end-to-end imitation-learning walkthrough.
• CLI cheat-sheet — quick reference for the lerobot-* commands.

The short version to run and train this policy:

Run the policy on your robot

lerobot-rollout \
  --strategy.type=base \
  --robot.type=picksodafromcabinet \
  --robot.port=<your_robot_port> \
  --robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
  --policy.path=jstm/molmoact2_single_arm \
  --task="Cook the item in the pan" \
  --duration=60

Replace the remaining <...> placeholders with your own values: --robot.port and the camera names/indices are specific to your machine, and the camera names must match the observation keys this policy was trained on.

When --strategy.type=base is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at rollout documentation.

Train your own policy

lerobot-train \
  --dataset.repo_id=${HF_USER}/<dataset> \
  --policy.type=molmoact2 \
  --output_dir=outputs/train/<policy_repo_id> \
  --job_name=lerobot_training \
  --policy.device=cuda \
  --policy.repo_id=${HF_USER}/<policy_repo_id> \
  --wandb.enable=true

Writes checkpoints to outputs/train/<policy_repo_id>/checkpoints/.

---

Evaluation

No evaluation results have been provided for this policy yet.

---

Citation

If you use this policy, please cite the method linked in the description above, along with LeRobot:

@misc{cadene2024lerobot,
    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
    howpublished = "\url{https://github.com/huggingface/lerobot}",
    year = {2024}
}