# Ru-Jev model sizes and sources

> Ru-Jev is a Russian-first decision model built on mmBERT-base with 307M parameters. It runs on CPU and has a separate scoring head.

Updated 2026-11-04 (Australia/Adelaide)

By besktech (beskvladimir-create) · First Hugging Face repository creation: 2026-11-01 · OPEN

A Russian-first typed-decision model built on mmBERT-base (307M), with a separate scoring head. It runs on CPU and supports yes/no, choice and ordinal scales. The maker says it is unaffiliated with TypeSafe AI and was not trained on [Jev](<https://decisionmodels.ai/models/jev>) outputs. Hugging Face now documents v1.1; the GitHub README still reports v1 results.

## Facts

- Size: 307M (mmBERT-base)
- Licence: Code MIT; weights tagged MIT on Hugging Face
- Run it: Load the backbone, head.pt and calibration.json using the Hugging Face card's Python example; the standard inference widget cannot load the separate head
- Release date: First Hugging Face repository creation: 01 Nov 2026; v1.1 card checked 03 Nov 2026

## Claims and sources

- **VENDOR-REPORTED**: For v1.1, the maker reports 0.825 micro accuracy and 0.0200 ECE on 13,373 decisions, half the validation split, with temperature fitted on the other half. Its 0.0159 ECE fitted and scored on the same data is in-sample. [source](<https://huggingface.co/besktech/ru-jev>)
- **VENDOR-REPORTED**: The v1.1 card reports full-validation accuracy of 0.965 on 60-intent routing and 0.954 on 18-scenario routing, but 0.522 on reasoning questions and 0.450 on three-way NLI. Category wording also changes routing accuracy. [source](<https://huggingface.co/besktech/ru-jev>)

## Links

- [Source: Weights and v1.1 model card](<https://huggingface.co/besktech/ru-jev>)
- [Source: GitHub](<https://github.com/beskvladimir-create/ru-jev>)
- [Source: Release metadata](<https://huggingface.co/api/models/besktech/ru-jev>)

## Related projects

No related projects are listed in the registry.