Training-free inference techniques with decision models

TypeLLM: Jev-inspired type-safe decoding for existing autoregressive LLMs on SGLang, with schema-guaranteed typed outputs.

Native Go runtime serving Gemma 4 12B as a Jev-like decision model with hand-tuned PTX kernels and no CGo or CUDA toolkit.

Go gateway exposing the Jev /v1/systemone contract over ordinary LLM backends by reading single-token label logprobs.

llama.cpp-based C++ server that turns any LLM into a System One decision model, reading answers from next-token logits.

Python library that finds numeric answers by bisection, asking Jev higher, lower or exactly at each guess.

Decision-forensics library that explains a Jev answer by ablating parts of the input and measuring how far the probability moves.

Turns any chat model on SGLang, vLLM, transformers or MLX into a Jev-compatible service with one prefill and one label token per question.

Self-hosted Jev-compatible System One server that sits in front of llama-server and reads option probabilities from any GGUF model.

Adapter that turns existing LLMs into Jev-style decision functions with option scores, optional calibration and review thresholds.

DeepSeek Harness jev_decide tool that brings the Jev decision paradigm to any OpenAI-compatible LLM, or to real Jev with a key.

OpenAI-compatible local server pairing a small llama.cpp model for generation with Jev for the closed decisions.

Decision sidecar and Copilot CLI pre-turn hook that mimics Jev choice, noul and score using Azure Foundry Cohere Rerank.

Toy chat that makes Jev talk by repeatedly choosing its next word from a tiny caveman vocabulary.

Python library that imitates Jev-style typed decisions (choice, score, yes/no) on local LLMs via Ollama, vLLM or llama.cpp.

MLX library that turns an existing local model into a decision engine by reading candidate logits, with no fine-tuning, on Apple Silicon.

Local browser app that turns Jev's per-pixel colour probability distributions into textured paintings.

Browser lab where Jev plays many 2048 games in parallel with one Choice per move and an editor for the state format it receives.

ChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.

Reads candidate logits from existing MLX-LM/VLM models on Apple Silicon to map state and a request to an allowed action.

Turns any local LLM into a Jev-style engine via masked-logit softmax, or proxies OpenAI-compatible APIs or Jev; includes a chat crush radar.

Single-script CLI and library for NLI classification and multiple-choice reranking with the AlexWortega/openjev Qwen3.5-4B cross-encoder.

Python library that turns an open LLM into a Jev-style classifier via constrained single-token choice indexes in one forward pass.

Open Jev-style decision model built on Gemma 3 270M with a scoring head, scoring all options in one forward pass on CPU.

Study of Jev's choices in multi-armed bandits, testing whether Bayesian instructions and supplied statistics improve its exploration.

Official code for the FastJEV paper: training-free reduction of redundant candidate computation in multimodal JEV-style models.

Local server (xks) implementing Jev's /v1/systemone contract on an open-weight LLM, accelerated with Xeon Phi cards.

A chatbot with no language model: every word is chosen by Jev Choice questions from thousands of options, with lookahead and self-critique.

Builds a Jev-style decision interface on Gemma 3 270M and measures what it takes: LoRA plus a pointer head reaches 0.821 AUC.

Research runtime that lets a bounded decision model like Jev operate over large tool, memory and context spaces via a virtual option space.

Educational C11 library and CLI that turns DiffusionGemma 26B into a CPU-first OpenJev-style decision engine reading candidate logits.