Jev Local

A ComfyUI node pack that branches a generation workflow on a plain-English question such as whether an image is too graphic for kids, running locally on Laya by default or Jev on a dropdown switch.

Cloudflare's decision models packaged for Ollama: pull clef for the 27B model or clef-flash for the 9B one and run classification, labelling, and routing locally with the same typed-question shape.

The Hugging Face hub for Laya's open System 1 checkpoints: the 421M English model at the repo root, a 322M multilingual build in a subfolder, and the typed-decisions fine-tune, all Apache-2.0.

The fine-tuned Laya checkpoint for four typed-decision workflows: 0.766 accuracy on 2,000 held-out decisions, above Jev 1.13.0's published 0.727 and the teacher self-agreement ceiling it trained past.

Supersonic Labs' 144.3M-parameter decision model on mmBERT-small: choice, score, and noul answers from supplied options in one pass, 73.15% on 2,000 typed decisions, Apache-2.0.

A browser WebGPU export of Julia 1: the same 551 MB decision checkpoint, a Rust WASM tokenizer, and a JavaScript API that answers typed questions client-side with no server or key.

An open distillation of Jev 1.13 onto Qwen3.8-27B: a 108.9M-parameter decision block answers typed questions in one prefill pass and adds a POST /v1/decide route beside a full System 2.

The vision sibling: the same text-trained System 1 head on Qwen3.8-27B's image encoder, taking images zero-shot, ranked first of 20 vision decision models on the community Jev Decision Index 0.3.

The 9B member of AutoTrust's Jev students: a 40.2M-parameter decision block on Qwen3.5-9B with 0.019 mean KL to Jev 1.13 and 70.7% HumanEval left untouched, small enough for one modest GPU.

AutoTrust's Gemma-based decision model with adaptive thinking: System 1 answers below 0.8 confidence hand off to the full Gemma 4 26B and mix the two by half, behind POST /v1/decide.

Liquid AI's 3.12B decision model built on LFM2.5-VL: state plus typed questions in one forward pass with zero output tokens, 48.57 on Decision Index 0.2.1 and 8 ms per decision on an RTX 4090.

An untrained readout: stock Gemma-4-31B weights plus a decider config that reads option letters at the answer slot, scored #2 of 70 on Decision Index v0.2.1 at 57.33 against Jev 1.13.0's 57.91.

GGUF builds of the Jev-Style v3 decision model on Qwen3.5-0.8B: a 0.53 GB Q4_K_M file the card says is decision-identical to FP32 on 240/240 parity rows, served through a pinned llama.cpp scorer.

Interfaze's 4B LoRA adapter over Qwen3.5-4B that speaks POST /v1/systemone: 0.807 held-out weighted accuracy and 0.061 ECE after calibration, with a 200,000-example training recipe documented.

Nace.AI's 8B decision model on NVIDIA's Efficient-DLM diffusion backbone: a 256-dim pointer head scores every option in one pass, behind the same POST /v1/systemone API as its hosted service.

A 400M-parameter Jev-compatible decision model with a browser build: 0.796 on typed decisions against Laya's 0.766, 17 ms per question on an L40S, and an ONNX file that runs in a tab.

The vLLM Semantic Router project's 29.37B decision model on Qwen3.8-27B: a probability per supplied option with zero generated tokens, 74.0 on JevArena and 56.5 on Jev Decision Index 0.2.1.

Superagent's security triage model: a continual fine-tune of AutoJev-27B that returns calibrated probabilities for prompt-injection and content checks, with a release policy at 0.70 unsafe.

FINAL-Bench's zero-token classifier: one forward pass plus a fitted temperature produce a full distribution over options, scoring 0.743 on the 2,000-decision typed-decisions test split.

Strands Agents' small decider for agent plumbing: routing, tool selection, triage, and guardrails from a 2B LoRA checkpoint that serves /v1/systemone locally or through a Python package.

A 4B scorer rebuilt from Qwen3-4B into a branching cross-encoder: one branch per option, no position bias, up to 256 options, and calibrated probabilities with no text to parse.

A 706,048-parameter form-filling scorer from Cua AI: given a UI element and candidate options it returns one probability per option, including check, click, and skip actions.

A 0.4B Jev-compatible decision model with measured order invariance: 960 random option shuffles moved no probability by more than 1e-5, and bev-decider serve exposes /v1/systemone.

An ultra-light Italian decision model: 400M Llama-based, a 465 MB Q8_0 GGUF, answering multiple choice with A–D tokens and booleans with TRUE/FALSE for edge and Rust use.

The official Laya playground: eight tabs that show choice, score, and noul decisions on ticket triage, phishing, guardrails, RAG filtering, moderation, routing, and multilingual text.

A ZeroGPU demo of Julia 1: define a state and any set of choice, score, and noul questions and see per-option probabilities rendered as bars and raw JSON.

Open recipe for calibrated decision models: an LLM teacher writes training data from a one-sentence task description, a LoRA plus decision head on Qwen3-4B-Base answers Choice, Score and Noul questions with calibrated probabilities, evaluated next to Jev on identical items.

Serves Shanghai AI Lab's Intern-Decision-0.8B vision decision model on Apple Silicon behind a /v1/systemone-shaped endpoint: screenshots plus typed questions in, calibrated Choice, Score and Noul probabilities out, for thresholding and escalation.

A native MLX runtime for Laya's open typed-decision weights: short decisions on Apple Silicon, with no generated tokens, PyTorch, or cloud API.

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.

A local Jev-compatible POST /v1/systemone server in TypeScript that maps typed questions onto oMLX classification prompts and normalizes logprob-style answers.

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.

Local macOS computer-use automation on Apple silicon using on-device laya typed decisions and CUA-S1-FORMS for filling, via the Accessibility API.

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.

A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.

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.

A Node and TypeScript package that runs Convai's Laya checkpoint through ONNX Runtime, with the same system_one shape as the Python reference.

A local /v1/systemone server that reads label probabilities from a GGUF chat model, with prompt repetition and a confidence shrink toward uniform.

A Python server in front of llama-server that reads one-token label probabilities and exposes them as POST /v1/systemone.

A local gateway that forwards /v1/systemone to TypeSafe, stores each call in SQLite, and draws the calls on a live map.

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.

A self-hosted System One server: one /v1/systemone contract, a Docker image each for Laya and kev, and a playground where snake, dino, and tetris call that endpoint.

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