Jev directory
CommunityJev Models & Reimplementations
UltraBERT Jev 380M (sigmoid-norm)
Fine-tuned UltraBERT-380M decision model on Hugging Face that scores a state, question, and option list in one forward pass. Uses sigmoid of yes minus no normalized over options; 72.8% dev and 71.9% test accuracy across 13 datasets, with an evidence head documented on the card.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Reads a state, a question, and a list of options and picks one option in a single forward pass, without generating text.
- Option k is scored from masked-token logits as sigmoid of " yes" minus " no", divided by the sum over options.
- Trained for one epoch at batch 32 and learning rate 1.5e-5 on the 13-dataset Reason+Long mixture with Nimble added.
- Reports 72.8% mean accuracy on the dev split and 71.9% on the test split across 13 datasets.
- Model card includes an Evidence head section alongside usage, related checkpoints, and limitations.
Questions about this entry
Short answers drawn from the linked project or page.
Load it with transformers AutoTokenizer and AutoModelForMaskedLM using the repo id, in fp32 via dtype=torch.float32, then move it to CUDA and call eval(). It was tested with transformers 5.20.2 and torch 2.9.
Both are UltraBERT-380M fine-tunes on the same 13-dataset mixture. This one scores options with sigmoid of " yes" minus " no" divided by the sum over options, and reports 72.8% dev and 71.9% test accuracy.
Yes. Masked-token logits are around 200 in magnitude, and bf16 weights changed accuracy by up to 8 points on long documents (MuSiQue). All reported numbers use fp32 weights.
No. The model was trained on a specific prompt format with the tokens " yes" and " no"; plain fill-mask use will not give the reported results, so the card's prompt must be used exactly.
Apache-2.0. It is a fine-tune of dmis-lab/UltraBERT-380M with 429,966,336 F32 parameters in one unsharded safetensors file.
arxiv:2610.02076, "LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them", and arxiv:2502.09604, "SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models".
It is an English encoder that picks one option per forward pass and generates no text. It requires the exact trained prompt format and fp32 weights, and the card documents limitations.
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
Fine-tuned UltraBERT-380M decision model on Hugging Face that reads a state, question, and option list and picks one option in a single forward pass. Scores options with a square-root softplus of yes minus no, normalized over options; 73.2% dev and 71.9% test accuracy over 13 datasets.
Jev Models & Reimplementations#open-models#arxiv#calibration
Community
arXiv paper presenting EDU-Jev, a family of single-pass System One decision models at 0.8B, 2B and 4B parameters that return a probability distribution over predefined education answer options without generating any text.
Jev Models & ReimplementationsArticle#arxiv#open-models#classification
Community
v-jev 1.4 is a Jev-style decision model on Hugging Face in 0.8B and 4B sizes, built on Qwen3.5 backbones. It returns probabilities for typed questions in one forward pass and adds value extraction and image decisions.
Jev Models & Reimplementations#open-models#classification#calibration
Community
A 7.7M-parameter decision model on Hugging Face that reads text or speech and returns one probability per option for choice, score, and noul questions. Speech runs through femto-asr, giving a 10.1M-parameter spoken pipeline.
Jev Models & Reimplementations#open-models#classification#local
Community
A Hugging Face checkpoint that fine-tunes UltraBERT-380M into a Jev-style decision model: it reads a state, a question and a list of options and picks one in a single forward pass. Reports 72.6% mean accuracy over 13 datasets on the test split.
Jev Models & Reimplementations#open-models#classification#local
Community
A 46M-parameter Russian and English decision model published on Hugging Face, tagged for classification, NLI, toxicity, moderation, and calibrated distillation. It ships a custom NQ4ForDecision class and a chat template with an optional thinking block.
Jev Models & Reimplementations#open-models#classification#calibration
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.