bridgequant-libero-76m

BridgeQuant 76M (TinyVL) trained jointly on the four LIBERO suites. LIBERO-500 mean-of-3: long 94.8 / spatial 98.0 / goal 96.2 / object 99.6 = 97.15; LIBERO-Plus 71.7.

Files: model.safetensors (trainable weights), norm_stats.json (state/action normalisation), bridgequant_vla.yaml / config.json / metadata.json (the bundle the loader expects), train_config.yaml (the experiment YAML used for training; evaluation and deployment take the same YAML).

Code: https://github.com/VLAOpt/bridgequant-async — load with load_trainable_weights(policy, "<this dir>") after BridgeQuantAsyncVLA.from_pretrained(config=cfg.policy, init_empty_trainable=True); for the SO101 arm use scripts/so101_policy.py (see docs/so101_deploy.md).