nvidia/Metatron-v1

Metatron v1

Choose an artifact

Package	Use	Documentation
G1/	Native PyTorch G1 inference: checkpoint, resolved config, reconstruction recipe and legal files	G1 model card, download and run
demo/model.onnx	Single-robot browser scene/recovery pipeline	Browser export card below
racer/network.onnx	Six-robot batched G1 Racer network	Browser export card below

The native checkpoint is 459,455,983 bytes (SHA256 e5fc2e47a8f9ee9b96a674cabbf236b3c510f887427645a14bc1779b10f0b43a). It retains the posterior and normalization statistics; the deterministic browser graphs export the prior/decoder path. Interfaces are not interchangeable. The native recipe masks scene inputs; see its card before re-exporting.

config.json is a machine-readable artifact index with file sizes and SHA256 digests, consumed by ProtoMotions' pinned native downloader. Model files are hosted here, not served by GitHub Pages. The existing browser paths are unchanged.

License

Model license: NVIDIA Open Model License. The full agreement and attribution notice govern model artifacts, including native weights and serialized configurations. Source code remains Apache-2.0. Dataset and asset rights are separate; this repository does not redistribute training motion clips.

• Deployment Geography: Global.
• Use Case: Researchers and developers running interactive humanoid control in a browser; the separate native G1 package also supports simulator and supervised real-G1 deployment workflows.
• Release: Metatron v1, hosted in this repository and integrated with ProtoMotions. Pin a Hub revision; no public ProtoMotions release tag is asserted here.

Browser export model card

Overview

ONNX inference exports of the unified Metatron G1 scene/recovery policy used by the Metatron browser demo and G1 Racer. Both files use the same learned policy weights, with different runtime interfaces. They are not interchangeable. The current exports are the epoch-6410 SAMP-capable unified student. Walking, scene interaction and recovery share one policy, with no separate recovery adapter.

Field	Value
Robot	Unitree G1, 29 controlled joints
Model	MaskedMimic-style transformer student with deterministic prior and decoder
Inference	Deterministic learned prior; FP32
Format	ONNX
Integration	ONNX Runtime Web with WebGPU or WebAssembly

Intended Use

Interactive humanoid control, locomotion and recovery evaluation with the matching browser applications. The applications provide physics, observations, task goals and control logic; the ONNX files alone are not complete demos.

Metatron supports deployment workflows beyond the browser, including other simulators and real G1 robots. These particular browser exports require their matching observation and control interfaces: compatibility is not a safety certification or a claim that these exact files have been validated on hardware.

Artifacts

File	Interface	Size
demo/model.onnx	Single-robot pipeline, including observation processing and action conversion	403,375,789 bytes
racer/network.onnx	Six-robot batched network; requires G1 Racer's separate observation processing	403,036,698 bytes

SHA256 digests:

• demo/model.onnx: 7180e82cae7ec04ff7766c262d430f57573d93678e025d8a71916885072a0cd4
• racer/network.onnx: 130a22718a34c0da488e2157553b40efedfefcf6ca6cb6b97cfdd67f8dfbeaf3

The Racer export changes graph organization and batching, not learned weights. Neither artifact is a resumable training checkpoint. Runtime code, robot assets, motion clips and application configuration are distributed separately.

Inputs and Outputs

The demo pipeline consumes current G1 state, eight historical state samples, paired incoming raw actions, nine-entry raw-action history, masked future pose/style/velocity goals and scene-box context (39 inputs). There is no recovery_enabled input. It returns joint PD targets (action), PD gains (stiffness, damping) and raw_action for history feedback. Recovery targets remain live runtime inputs, not baked goals. Applications use staged local goals with independent per-robot recovery state.

G1 Racer computes observations outside the neural graph and evaluates all six robots in one batch. Its network exposes action and raw_action; controller parameters come from the paired runtime. Do not feed raw demo inputs directly to this network or change its batch size without rebuilding and validating it.

Preserve the paired application's joint/body ordering, quaternion convention, history ordering, normalization, target masks, control rate and action mapping. Use the matching runtime manifest and ONNX tensor signatures for exact layouts.

Runtime Support and Validation

The browser integrations use MuJoCo WASM for simulation and ONNX Runtime Web for inference. WebGPU is recommended on capable devices; CPU/WASM is a fallback and does not guarantee real-time six-robot operation. GPU drivers, browsers and hardware affect startup time and throughput.

The six-robot ONNX and compiled-observation paths were checked against the single-robot demo export on 60 distinct/history-perturbed test states, with maximum absolute action error 5.55e-6. Recovery height, recovery timing, action history and scene inputs were independently varied and affected the outputs. These are numerical export checks, not task-success or real-robot benchmarks. Racer's paired application also runs action-parity fixtures at startup.

For reproducibility, pin downloads to a repository commit rather than main. Public browser delivery requires anonymous access to the files; never embed a Hugging Face access token in client-side code.

Limitations and Safety

• Recovery, balance and tracking can fail, especially outside the evaluated states, terrain and command distribution.
• Game launch assists, low-gravity zones and respawns are application mechanics, not capabilities guaranteed by the learned policy or physical robot.
• The model is not a collision-avoidance system or a safety controller.
• Hardware use requires independent validation, appropriate joint/torque limits, supervised testing, and an emergency-stop mechanism.
• These exports are not a complete training-reproduction package. No training dataset or training checkpoint is included.

License and Asset Rights

Model terms: NVIDIA Open Model License Agreement, with the required attribution in NOTICE.txt. The complete agreement governs; this card does not replace or extend it.

Model licensing does not grant rights to motion datasets, recovery reference clips, robot meshes, game assets or third-party runtime software. None of those assets is included in this model repository. Obtain them through their respective distributions and follow their separate terms. Permission to include a clip inside a demo or game does not imply permission to redistribute that clip as a standalone dataset.

These ONNX exports are publicly available for anonymous download. Their availability does not change the separate distribution terms or release status of the associated application bundles, motion clips and other assets.

References

• ProtoMotions
• ProtoMotions documentation
• NVIDIA Open Model License

Download statistics

Hub download totals are server-side query-file request counts, not unique users or game sessions. The native downloader reads the functional config.json artifact index; it does not send a separate analytics request. Locally cached loads do not request model files again. The existing ONNX loaders remain pinned to their own artifacts; adding the native package does not retroactively measure browser usage. Library-specific counting can differ; see Hugging Face download statistics.