Jev directory
CommunityJev Models & Reimplementations
LLM As Jev
Hugging Face model repo hosting llm-as-jev, a fine-tune of Qwen/Qwen3-0.6B tagged for decision-model and multiple-choice work. Ships safetensors weights, a transformers configuration, and an Apache-2.0 license.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Fine-tune of the Qwen/Qwen3-0.6B base model, published under the llm-as-jev and decision-model tags.
- Listed with the multiple-choice pipeline tag and the transformers library, loading through AutoModelForCausalLM.
- Weights are stored in safetensors format and the repository is marked endpoints_compatible.
- Licensed Apache-2.0; the repo is public and not gated.
- Recorded 9 all-time downloads and 0 likes, created and last modified on 2026-10-30.
Questions about this entry
Short answers drawn from the linked project or page.
It is a fine-tune of Qwen/Qwen3-0.6B, a roughly 0.6B-parameter Qwen3 model. The repository tags record both base_model:Qwen/Qwen3-0.6B and base_model:finetune:Qwen/Qwen3-0.6B.
The repo is tagged with the transformers library and AutoModelForCausalLM, with weights in safetensors format, so it loads through the standard transformers causal language model path.
The repository is published under the Apache-2.0 license, and it is public and not gated, so no access request is needed to download the weights.
Its pipeline tag is multiple-choice, and it carries the additional tags decision-model and llm-as-jev alongside text-generation, indicating use for picking among labeled options.
The repository's chat template handles tool definitions inside tools tags, emits function calls as JSON in tool_call tags, and separates reasoning content into think blocks when present.
The repository records 9 all-time downloads and 0 likes, with creation and last modification both dated 2026-10-30. It is a small, recently published upload.
It is a 0.6B-parameter fine-tune with no published evaluation numbers and no inference providers listed, so it is a poor fit when you need calibrated probabilities or hosted serving guarantees.
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
Full-parameter fine-tune of Qwen3.5-4B for medical multiple-choice scoring. Given a case and candidate options, it returns the chosen option key with per-option probabilities as short JSON, without explanations or chain-of-thought.
Jev Models & Reimplementations#open-models#classification#python
Community
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
A JEV decision model built on inclusionAI/Ling-3.0-tiny with AReno, shipping a decision head and rank-128 backbone LoRA adapters. Serves choice, noul, and score questions over an areno /v1/systemone endpoint on Apple Silicon MLX and CUDA.
Jev Models & Reimplementations#open-models#local#python
Community
Hugging Face text-classification checkpoint from Sagicc: a 4.9M-parameter F32 safetensors model with custom code, MIT licensed, documented with JEV decision APIs through AutoModel and a FastAPI server.
Jev Models & Reimplementations#open-models#python#local
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.