satoshi3/attune-l3cA

Attune Vector Level 3 policy (vector_v1.1)

A fine-tune of domFree/attune-j4 at revision 4a2651b08cb70332bfe9b86ef9b2efaff1825eb8, for the Robotensor Attune Vector lane (Level 3).

• Weights: model.safetensors, sha256 fa7bb3bdc2c255ca548b4d4c9d1ebee988f0430b52293c9456e85ac94dd23137. Same 753-tensor vector_v1.1 layout as the parent.
• Unchanged from the parent: the CLIP vision encoders, the action/proprioception normalizers, the proprioception and prompt-pool layers. Trained: the transformer decoder, the diffusion U-Net, and the position/sink embeddings.
• Training: 10,000 steps, batch 64, learning rate 1e-5 (cosine), EMA 0.999, epsilon-prediction diffusion loss. Conservative targeted adaptation: about 55% of imitation samples from the four weakest tasks (beat_block_hammer, place_mouse_pad, place_dual_shoes, move_stapler_pad), plus a function-space anchor to the frozen parent on the other twelve tasks (weight 2).
• Data: Level 3 expert demonstrations generated with the RoboTwin-Vector harness (franka-panda, public seed range below 2,000,000), each target prompted with an expert demonstration from a different scene of the same task.

The parent repository declares no license; this card makes no claim beyond what the parent's terms allow.