Mapika/decider

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

[](https://github.com/Mapika/decider/actions/workflows/tests.yml) [](https://huggingface.co/Mapika/decider-2b) [](LICENSE) Ten text games and Super Mario Bros, each move one typed decision over the legal actions; see decider/games/ and docs/HISTORY.md. A language model that does not generate text. It reads a state and a set of typed questions and returns, from one forward pass, a probability distribution for every question. There is no decoding, no parsing, and no output outside the options you defined. It is an open reproduction of the "System One" model class (TypeSafe AI's Jev), released as a 2B model built on Qwen/Qwen3.5-2B-Base and a 35B mixture-of-experts model built on Qwen/Qwen3.5-35B-A3B-Base. Contents: Models · Quick start · What it does · How it works · Results · Train · Serve · Repository layout · Changelog · Limitations The v8 weights stay available under the Hub tag v8. docs/HISTORY.md describes every version. examples/ has three complete programs (confidence-gated routing, composite scoring, a hierarchical beam over…

Mapika/decider on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-09-21T12:28:06.866Z

Inside the original README — Document outline
  1. decider: one-pass typed decisions with calibrated probabilities
  2. Models
  3. Quick start
  4. What it does
  5. How it works
  6. Results
  7. decider-35b-a3b against decider-2b v10
  8. The 94 public tasks
  9. External suites
  10. Speed
  11. Train
  12. Serve

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

Repository facts

Owner
Mapika
Primary language
Python
Stars
256
Forks
6
Open issues + pull requests
1
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-09-16T07:15:09.000Z
Last push
2026-09-20T09:40:14.000Z

Topics and intended use

No topics were included in the latest source metadata.

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-09-21T12:01:32.144Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent