Jev directory
CommunityJev Models & Reimplementations
WorkMagic Jev Decision Qwen3 8B SFT v1
LoRA fine-tune of Qwen/Qwen3-8B published by workmagicio and tagged as a Jev decision model for typed decisions. Distributed in safetensors under the anyjev library name, with an English conversational text-generation pipeline.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- LoRA adapter fine-tuned from the Qwen/Qwen3-8B base model
- Tagged decision-model, typed-decisions, tacit, and anyjev
- Safetensors weights, English, text-generation pipeline
- 141 all-time downloads and 0 likes at the time of the listing
- Public and ungated, created 2026-11-01
Questions about this entry
Short answers drawn from the linked project or page.
It is a Hugging Face model repository from workmagicio containing a supervised fine-tune of Qwen/Qwen3-8B. The listing tags it as a Jev decision model for typed decisions, with the anyjev library name and a conversational text-generation pipeline.
The repository metadata lists Qwen/Qwen3-8B as the base model and as the adapter base, so the release is a LoRA adapter over that Qwen3 8B checkpoint rather than a from-scratch model.
The repository provides safetensors weights and is tagged as a LoRA adapter. The declared library name is anyjev, and the pipeline tag is text-generation with conversational support.
The repository metadata lists English as the only language tag. No other language coverage is declared in the listing material.
The listing reports 141 all-time downloads and 0 likes. The repository is public and ungated, and it was created on 2026-11-01.
The provided listing material does not state a license for this repository. Check the model page for the license field, and note that the Qwen3-8B base model may carry its own terms.
The listing publishes no benchmark, calibration, or accuracy numbers, and it is labeled SFT v1. Treat it as an early adapter and measure it on your own decision data before relying on its outputs.
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
Hugging Face LoRA adapter from workmagicio, fine-tuned from Qwen/Qwen3-8B and tagged decision-model and typed-decisions. Published under library anyjev with safetensors weights for English text generation.
Jev Models & Reimplementations#open-models#lora#typed-decisions
Community
A LoRA plus 24-slot decision head over Qwen3.8-27B from Ming Xu's train-jev project: it serves TypeSafe's System One API with 0.851 Kev transfer-v4 accuracy and ECE 0.053, and needs an 80 GB GPU.
Jev Models & Reimplementations#community#open-models#local
Community
A 24 GB-GPU alternative from the train-jev project: Qwen3.5-4B plus a rank-16 LoRA and 24-slot decision head scoring 0.647 PK accuracy, 40.4 Decision Index and 43 ms p50 latency, ahead of Kev-4B at the same size.
Jev Models & Reimplementations#community#open-models#local
Community
A LoRA fine-tune of Strands Decider 2B that rates jokes on seven comedy traits, answering each as a typed yes/no question with a probability; an unofficial fan project that cannot write jokes and is not endorsed by Conan O'Brien.
Jev Models & Reimplementations#community#open-models#humor
Community
A native MLX runtime for Laya's open typed-decision weights: short decisions on Apple Silicon, with no generated tokens, PyTorch, or cloud API.
Jev Models & Reimplementations#community#python#open-models
Community
mizorewww/laya-mlxPython
mizorewww/laya-mlxPythonAn open-model semantic-if engine positioned as a local Jev-style decision stack, separate from the original SemIf repo but sharing the same author.
Jev Models & Reimplementations#community#python#open-models
Community
TheoLeeCJ/SemIf-OpenJevPython
TheoLeeCJ/SemIf-OpenJevPythonFrom 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.