bridgequant-robotwin-7m-hammer

BridgeQuant 7M trained on RoboTwin 2.0 beat_block_hammer (50 clean demos, Aloha-AgileX 14-D, relative arm joints). 40/100 success in the RoboTwin 2.0 clean setting with the XPolicyLab policy-server protocol (scripts/robotwin_policy_server.py).

Files: model.safetensors, norm_stats.json, bridgequant_vla.yaml / config.json / metadata.json (the bundle load_trainable_weights expects), train_config.yaml (the experiment YAML; evaluation and deployment use the same YAML).

Code: https://github.com/VLAOpt/bridgequant-async