snupilab/humanoidtoolbench-fastwam-sim-3003

HumanoidToolBench FastWAM: Simulation training, 3,003 segments

The validated final policy checkpoint is available in this repository.

This is a HumanoidToolBench training-result repository. It does not substitute an upstream pretrained policy for a HumanoidToolBench-trained checkpoint.

Pinned training data.

The simulation pool contains 1,200 successful L1/L2 demonstrations and 1,803 extracted L0 prefixes, spanning 18 conditions. The 3,003 segments are not 3,003 independent demonstrations.

Use the model's native HumanoidToolBench adapter and model-specific dependencies. This repository does not claim compatibility with arbitrary Transformers or simulation loaders. No evaluation score is claimed by checkpoint publication.

Native FastWAM weights contain mot and proprioencoder. Use HumanoidToolBench fastwamserver with --config-dir configs --task thetag1 --dataset-stats run/datasetstats.json and the final weight. Set THETAFASTWAMACTIONDIT to the external initialization file matching inference_dependencies.json. Pre-cache its declared Wan2.2, T5/VAE and tokenizer dependencies. The native constructor loads those assets before trained weights, and native mot loading uses strict=False. This release does not establish standalone/offline loading or a new native inference qualification.

Training uses independent model optimizers and shared GPU execution through MPS. Publication is performed by a CPU uploader after final checkpoint validation.