OPEN

JevAlt decision model

JevAlt offers local 4B decision models for English, Turkish and German. Read its unknown-answer option, licence and recorded evaluation limits.

By Mert Kaya (Eschatia Labs) · October weights; catch-up discovery: 1 Oct 2026

Three Intern-Decision-4B fine-tunes: Deem-4B for English, Karar-4B for Turkish and Wähler-4B for German. They return per-option probabilities through the System One API. Optional extensions add unknown, conformal answer sets or a short generated reasoning trace; reasoning is off by default. This is a catch-up October release.

Quick answers

What is JevAlt by Mert Kaya (Eschatia Labs)?

JevAlt: Three Intern-Decision-4B fine-tunes: Deem-4B for English, Karar-4B for Turkish and Wähler-4B for German.

JevAlt facts · Source: github.com ↗

Who makes JevAlt?

JevAlt: Mert Kaya (Eschatia Labs)

JevAlt facts · Source: github.com ↗

Are JevAlt's weights open?

JevAlt: Full weights, Q4_K_M/Q5_K_M/Q8_0 GGUF, Transformers and llama.cpp server Licence: Apache-2.0 code and weights; dataset terms remain separate

JevAlt facts · Source: github.com ↗

Make a first local request

The local guide follows JevAlt's documented Python setup, default Deem GGUF server and typed support-ticket request. Saved author-run examples are linked separately from the setup commands.

First local JevAlt request

Source

Facts

Size
4B per language model
Inputs
Text; English, Turkish or German by model
Limits
8k context; up to 62 choice options; score uses 2 to 10 levels
Licence
Apache-2.0 code and weights; dataset terms remain separate
Access
Full weights, Q4_K_M/Q5_K_M/Q8_0 GGUF, Transformers and llama.cpp server

Claims and sources

Links

Related projects

All projects · Back to the model registry