bridgequant-so101-76m-ptr5

BridgeQuant 76M SO101 teacher retrained with loss.phase_transition_radius: 5 (wider loss window around gripper transitions; everything else identical to twanghcmut/bridgequant-so101-76m). Same three tasks, same data.

Files: model.safetensors, norm_stats.json, bridgequant_vla.yaml / config.json / metadata.json, train_config.yaml (the teacher paths inside are only needed for training; inference ignores them).

Code: https://github.com/VLAOpt/bridgequant-async — scripts/so101_policy.py, guide in docs/so101_deploy.md.