mini-jev
Small personal model trained in the spirit of Jev; few public details beyond a one-line description.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
mini-jev by van5hdeep is listed as a simple model trained with Jev as inspiration. No README was available, so details such as the base model, training data, supported question types and evaluation are unknown.
Based on the list description, it likely aims to map a state and question to a fixed set of options in the way Jev does, but this cannot be confirmed from the sources. Treat it as an early personal experiment and check the repository directly before relying on it.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Pick one option for the given input (inferred from the Jev inspiration)(inferred) | — |
How it works
- Provide input state and a question (inferred).
- Model scores the allowed options (inferred).
- Use the top option in your application (inferred).
Strengths
- Open repository for experimenting with a Jev-like small model.
Caveats
- No README; architecture, data and accuracy are undocumented.
- Maturity and licence unknown.
At a glance
- Type
- Model
Use cases and integrations
How curated lists describe it
a simple model trained on inspiration of jev.
wh000wh000/awesome-jev-live
Frequently asked questions
What is this project?
A simple model trained with Jev as inspiration, according to its list entry.
Is there documentation?
No README could be fetched, so usage details are unknown.
Does it need a TypeSafe key?
Unknown; as a self-trained model it presumably does not, but the sources do not say.
Related projects
Mangaba AI's local, calibrated typed-decision model for Portuguese text, trained to optimize the Brier score; proprietary since v5.
ProjectproductionPython- TypeAR★ 946
TypeLLM: Jev-inspired type-safe decoding for existing autoregressive LLMs on SGLang, with schema-guaranteed typed outputs.
ProjectbetaPython - blink★ 22
Open one-pass typed-decision model with a dependency-free C99 runtime that also builds to a 66 KB WebAssembly module.
ServicebetaC - Foq★ 11
Local open alternative to Jev using a 1.58-bit ternary 8B model to answer booleans, choices, scores and Pydantic extraction in ~25 ms.
ProjectbetaPython Free hosted Jev-style multimodal decision model API (about 20B active) that picks actions from images and options, aimed at robot control.
ServicebetaRuns the open Laya decision model entirely in a browser tab with WebGPU and ONNX Runtime Web: no server, no API key.
ServicebetaTypeScript