Jev directory
CommunityJev Models & Reimplementations
Jev-Style-2B-Decision-v4-GGUF
Hugging Face repository hosting GGUF weights for Jev-Style-2B-Decision-v4, a 2B Jev-style decision model published under the chaoliangUNSW account. The listing includes a chat template that renders messages, reasoning content, tool calls, and vision inputs.
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Distributes GGUF weights for a 2B Jev-style decision model, version v4.
- Hosted on Hugging Face under the chaoliangUNSW account.
- Repository page includes a chat template rendering system, user, assistant, and tool messages.
- Template defines XML-style tool calls with tool_call and function blocks.
- Template splits reasoning content on think tags and emits image and video pad tokens.
Questions about this entry
Short answers drawn from the linked project or page.
It is a Hugging Face model repository that distributes GGUF weights for a 2B Jev-style decision model, version v4, published under the chaoliangUNSW account.
The repository distributes GGUF files. GGUF is a quantized weight format consumed by local inference tooling rather than by the official Python and TypeScript SDKs directly.
No. The material available here is the repository listing and its chat template. It does not state benchmark scores, calibration measurements, or accuracy figures for this checkpoint.
It renders system, user, assistant, and tool messages, wraps tool responses in tool_response tags, splits reasoning content on think tags, and emits image and video pad tokens for vision items.
The listing does not include a run script or SDK example for this checkpoint. GGUF weights are loaded through local inference tooling that supports the format.
It is published under the chaoliangUNSW Hugging Face account. The listing does not identify the checkpoint as an official TypeSafe AI release.
The available listing material does not state a license, so check the repository page metadata before redistributing or shipping the weights in a product.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker 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 NewsMore Jev resources like this
A 26M-class decision model on Hugging Face, fine-tuned from q-project/N-Q-26M-Chat. It ships a custom NQ4ForDecision class for text classification and feature extraction, is tagged calibrated and decision-model, and publishes Apache-2.0 weights with Russian and English support.
Jev Models & Reimplementations#open-models#calibration#classification
Community
An independent, from-scratch reconstruction of a Jev-style decision model that never generates text: a state plus typed questions returns a probability for every option. Trained on Qwen3-0.6B and 1.7B backbones with LoRA and served through a system_one-shaped API.
Jev Models & Reimplementations#open-models#python#research
CommunityES7/JEV-from-Scratch
Open Jev-style decision model built on LiquidAI's LFM2.5-350M backbone, a clone of kev. Serves the System One API contract so the TypeSafe SDK works against a local server, returning probabilities for typed questions from one forward pass.
Jev Models & Reimplementations#open-models#python#local
Communityfranckverrot/lev
Apache-2.0 Hugging Face repository for RSI-JEV-27b, a 27B multimodal decision model based on Qwen3.8-27B that answers supplied multiple-choice questions over images, returning a selected option and probabilities for all options in one forward pass.
Jev Models & Reimplementations#open-models#benchmark#calibration
Community
Satirical Python script that answers a query with DO or DO_NOT plus a random confidence percentage, presented as a natural alternative to Jev. MIT-licensed, Python 3.8+, one dependency, no API keys or model weights.
Jev Models & Reimplementations#github#python#open-models
CommunityAhmad170412/Koin
Russian-first open typed-decision model on Hugging Face. Given a context and a set of candidate options it returns a calibrated probability and picks one, covering yes/no, choice, and ordinal scale decisions. Built on mmBERT-base with 307M parameters under an MIT license.
Jev Models & Reimplementations#open-models#calibration#classification
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.