VLAOpenReadiness 73/100Provisional

Fast Action Tokenizer

lerobot

This is the official repo for the FAST action tokenizer.

Code: Unverified
Weights: Unverified
Checkpoint: Unverified
License: apache-2.0

Weights Model index A–Z

Decision summary

Best for

VLA training

Main blocker

Training data requirements are not structured enough for reliable dataset matching.

Next check

Verify weight files, sizes, format, and loading instructions.

Release history

Source-backed release timing for this canonical model record.

Important releases

2026-02-14
Checkpoint published
Release timing is recorded from the official source creation date.
Official source

Selection readiness

Evidence dimensions for deciding whether this model is ready to inspect, compare, or adopt. Scores describe catalog evidence, not task performance.

Published evaluation

How scores work

73/100

Provisional

2/6 dimensions scored · 33% confidence

Access and governance75conf. 85

Artifact availabilityNot scoredconf. 15

Training and loading reproducibility70conf. 65

Training data requirementsNot scoredconf. 15

Evaluation evidenceNot scoredconf. 10

Deployment readinessNot scoredconf. 10

Engineering checks (OBRS) behind this record

Engineering checksBronze

Needs Audit

4/12checks passed

OBRS metadata and reported test evidence. A breakdown behind Selection readiness, not a separate score or an independent OpenBot certification.

Standardization & Loaders2 / 25 pt

Physical & Action Quality12 / 25 pt

Semantic & Annotation15 / 20 pt

Real-World Validation0 / 15 pt

License & Compliance10 / 15 pt

Missing evidence and readiness gaps

A passing real-hardware test report is required.
A passing ingestion/pipeline test report is required.
A passing privacy and provenance review is required.

Why these scores

The strongest decision reasons behind Selection readiness.

Top 3 adoption signals

Artifact availability

Unknown

Code and weights are not verified.

— · confidence 15

Training and loading reproducibility

Useful

Configuration files are present; runtime loading is not tested.

70 · confidence 65

Evaluation evidence

Unknown

No structured evaluation evidence has been verified.

— · confidence 10

Data requirements

Declared loop-data needs, missing evidence, and the next checks that matter.

2 required categories

Language intent / task phase

language

required

Action / robot state

actions

required

Critical gaps

Core categories are represented. Interface alignment and data quality still require verification.

Linked datasets

Signal-level links only. Verify runtime interfaces before use.

Browse datasets

No related catalog datasets are linked to this model yet.

More evidenceShow

Additional decision dimensions

Access and governanceUseful

Access and license are declared by the source.

75 · c85

Training data requirementsUnknown