Skip to content

mini-Jev

A preregistered measurement of a Jev-style interface on frozen Qwen3-4B: read the option letter's logits instead of generating grammar-constrained JSON.

Stars
59
Language
Python
License
MIT
Published by
Community
Author
r-ms
Last verified
Sep 2026

r-ms/mini-jev

User repository on GitHub

View on GitHub

mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.

Forks
5
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

What a Jev-style interface looks like on a frozen model: classify against a schema that arrives with the request by reading next-token logits, not by generating JSON. Measured on Qwen3-4B. TypeSafe's Jev is trained for typed decisions without open generation. mini-Jev asks how much of that interface an ordinary frozen model already provides, and measures it against today's path, grammar-constrained JSON.

Quoted from the project's README. Read the full README.

Highlights

  • On 6,750 paired observations, reading the letter scored 0.907 against grammar-constrained JSON at 0.909.
  • The most likely next token was an option letter in 13,600 of 13,600 questions.
  • At 32 tokens, reading the letter took 0.24× the time of JSON. A shared-prefix cache kept the lead on 2,048-token texts.
  • Reading a letter beat writing the option's name by 10.0 points on intent.

Watch out

MIT. This does not call TypeSafe. Strings and numbers are still generated. On out-of-scope texts, JSON picked none-of-the-above on 47 of 50 and letters on 41 of 50. Runs are Qwen3-4B-Instruct-2507, bf16, greedy.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

Hacker News: mini-Jev reads option-letter logits on a frozen Qwen3-4B instead of generating JSON.

phyrex3 pointsMini-Jev – typesafe's Jev implemented on top of an LLM locallyRead the thread on Hacker News

LinkedIn: What multimodal decision models actually change, and what they do not.

LinkedInJevDirectory.org

Hacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.

1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker News

Related terms

Glossary definitions related to this entry.

More Jev resources like this

6.9kGitHub stars
A native MLX runtime for Laya's open typed-decision weights: short decisions on Apple Silicon, with no generated tokens, PyTorch, or cloud API.
Jev Models & Reimplementations#community#python#open-models
4.8kGitHub stars
An open-model semantic-if engine positioned as a local Jev-style decision stack, separate from the original SemIf repo but sharing the same author.
Jev Models & Reimplementations#community#python#open-models
1.6kGitHub stars
Laya typed decisions through Apple Core ML and the Neural Engine, with the author's speed and energy benchmarks for short decisions on an M3 Max.
Jev Models & Reimplementations#community#python#open-models
1.3kGitHub stars
A local yes/no decision model that speaks Jev's wire format on a laptop CPU, refusing Choice and Score until those question types ship.
Jev Models & Reimplementations#community#python#open-models
877GitHub stars
A local server that reads next-token probabilities from a fine-tuned Spark model and returns Choice, Score, and Noul answers with zero generated tokens.
Jev Models & Reimplementations#community#python#open-models
58GitHub stars
An Apache-2.0 decision engine with a TypeSafe-compatible endpoint, document answers with source passages, and a ViZDoom demo that picks actions from structured game state.
Jev Models & Reimplementations#community#python#local

From the Jev guides

Original write-ups on what this entry is for.

Interface, size, license, claims — in that order. A selection guide across the system-one catalog, from a 706K form scorer to 27B Jev students.
Jev Practices & Patterns#open-models#evaluation#benchmarks
Read article
Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.
Jev Models & Reimplementations#open-models#hugging-face#local
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai