Jev directory
CommunityJev Models & Reimplementations
nanoGentzen-Jev-v3
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.
- Reading time
- 1 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- 4,927,780 F32 parameters in a single unsharded safetensors file of about 19.7 MB.
- Tagged text-classification and feature-extraction; loads with trust_remote_code=True.
- Custom class modeling_nanogentzen.GentzenPolicyValueModel is loaded through AutoModel.
- Model card documents AutoModel.decide and AutoModel.system_one plus a FastAPI server.
- MIT licensed, English, region US, with no inference providers enabled.
Questions about this entry
Short answers drawn from the linked project or page.
Use transformers with trust_remote_code=True, for example AutoModel.from_pretrained("Sagicc/nanoGentzen-Jev-v3", trust_remote_code=True, device_map="auto"). A pipeline("text-classification", model="Sagicc/nanoGentzen-Jev-v3", trust_remote_code=True) call also works.
It holds 4,927,780 F32 parameters in a single unsharded safetensors file of about 19,718,200 bytes. The repository reports it as not quantized, and no quantizations are listed.
The model is published under the MIT license, and the repository is public and not gated.
It documents dual JEV decision APIs: AutoModel.decide and AutoModel.system_one in Python, a FastAPI server exposing /v1/decide and /v1/systemone, and a command-line interface in cli.py.
The card references a LocalLLaMA/typed-decisions benchmark covering 400 test cases and 2,000 decisions, and the repository carries an eval-results tag.
The pipeline tag is text-classification, with transformers, safetensors, and PyTorch listed as libraries. The custom class is modeling_nanogentzen.GentzenPolicyValueModel and the auto model is AutoModel.
It is a small research model with minimal adoption, showing 3 downloads and 0 likes, and no inference providers are enabled. Expect to run it locally with custom code rather than through hosted inference, and treat the model card as the only documentation.
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
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.
Jev Models & Reimplementations#open-models#local#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
A 561M-parameter XLM-RoBERTa-large decision model given one extra training epoch on Jev's answers, with about 23% of examples black-box distilled from Jev's public API. Supports noul, choice, and score questions in 18 languages and loads through the bundled naluri.py.
Jev Models & Reimplementations#open-models#calibration#benchmark
Community
MLX builds of Jev-Style-2B-Decision-v4 for Apple silicon: bf16 (3.76 GB) and 8-bit (2.00 GB) folders for text and JSON states, run through one shared jev_style_decision_mlx.py runtime under Apache-2.0.
Jev Models & Reimplementations#open-models#calibration#local
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.