Julia 1 decision model
Julia 1 is a 144M multilingual decision encoder with CPU inference. Read its typed questions, native option limits and separate CPU results.
By Supersonic Labs · Published weights and Python runtime; September catch-up: 25 Sep 2026
A 144.3M-parameter multilingual encoder adapted from mmBERT-small to score supplied options. It accepts named Choice, Noul and ordered Score questions, with a Python runtime for CPU or CUDA. This September release was found through an overnight card edit.
Quick answers
What is Julia 1 by Supersonic Labs?
Julia 1: A 144.3M-parameter multilingual encoder adapted from mmBERT-small to score supplied options.
Who makes Julia 1?
Julia 1: Supersonic Labs
Are Julia 1's weights open?
Julia 1: Open weights and packaged Python inference code; private training pipeline Licence: Apache-2.0 declared in the card; no separate package licence file
Facts
- Size
- 144,292,870 stored parameters; FP32 weights
- Inputs
- Text state and 2 to 20 options per native question
- Context
- 8,192 combined tokens supported by the runtime; historical accuracy tests used 1,024
- Access
- Open weights and packaged Python inference code; private training pipeline
- Licence
- Apache-2.0 declared in the card; no separate package licence file
Claims and sources
- The maker reports 1,463/2,000 typed questions correct on H200 BF16. A separate CPU FP32 reproduction gets 426/600 Choice, 542/800 Score and 483/600 Noul. Jev figures in the card are supplied references, not newly matched calls; an 8,192-token smoke test does not establish accuracy at that length. vendor reportedsource
Links
Source: Card, runtime and weights → Source: CPU results → Source: Checkpoint provenance →
Related projects
No related projects are listed in the registry.