SO-101 (SO-ARM101) · published weights
Generalist SO-101 pick and place (world action model, fine-tune with the included LoRA recipe)
Record
- Robot
- SO-101 (SO-ARM101) therobotstudio/so-101
- Framework
- LeRobot (Flux3Policy) · LeRobot
- Policy license
- not stated by the package · robot software repos: Apache-2.0
- File
- model.safetensors
- Note
- Black Forest Labs FLUX 3 Action, 7B. Trained on the SO-101 episodes of lerobot/community_dataset_v3. Two cameras (scene + wrist), 6-D joint-delta actions with absolute gripper, 30 Hz. FLUX Kommunity License: non-commercial use unless you are a qualifying user; needs a large GPU.
Not in the tab yet
To replay this policy in the browser we need an ONNX export of the named checkpoint, the observation and action contract copied from the authors' own sim2sim or deploy script, and a MuJoCo model of the robot that the contract matches. Then it must walk 60 s in our runtime without a fall. Until then the source link is the way in.
Other SO-101 (SO-ARM101) policies · 2
- SO-100/101 language-conditioned manipulation (VLA, zero-shot or fine-tune)LeRobot (MolmoAct2)
- SmolVLA base (pretrained VLA to fine-tune on your own SO-101 dataset)LeRobot (SmolVLA)