Jev directory
CommunityJev Models & Reimplementations
Jev Spam Decision 2B
Hugging Face model repository for abidlabs/jev-spam-decision-2b, a 2B-scale model aimed at spam decisions. The published model page includes a Jinja chat template covering tool calls, reasoning blocks, and image or video content.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Hosted on Hugging Face as abidlabs/jev-spam-decision-2b.
- The name indicates a 2B-parameter model targeting spam decisions.
- The model page publishes a Jinja chat template with tool-call formatting.
- The template handles reasoning content plus image and video placeholders.
- Chat turns are marked with <|im_start|> and <|im_end|> tokens.
Questions about this entry
Short answers drawn from the linked project or page.
It is a model repository on Hugging Face. The name indicates a 2B-scale model aimed at spam decisions, and the model page publishes a chat template alongside the model files.
It is published on Hugging Face under abidlabs/jev-spam-decision-2b, so it can be fetched with standard Hugging Face tooling. The available material does not include install commands or a usage snippet.
The published Jinja template uses <|im_start|> and <|im_end|> markers, allows an optional system block at the start, and wraps assistant reasoning content in think tags.
Yes. The template renders a tools section and instructs the model to reply with tool_call blocks containing function and parameter entries, with no suffix after the call.
The template includes vision handling, emitting vision_start and vision_end markers around image and video pads, and it raises an exception if images appear in a system message.
The provided material does not state a license for this repository. Check the model page on Hugging Face for the license and any usage terms before relying on it.
The repository sits under the Hugging Face user abidlabs. The available material contains no benchmark numbers, training data, evaluation results, or maintainer notes, so calibration is unverified here.
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
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 1.7B-parameter SocialJev preview model on Hugging Face, fine-tuned from Qwen3-1.7B for typed classification in the social sciences. Runs through Transformers with trust_remote_code or the social-jev package with a vLLM backend, returning a choice and probabilities per query.
Jev Models & Reimplementations#open-models#classification#python
Community
A 4B-parameter SocialJev preview model on Hugging Face, fine-tuned from Qwen3-4B for typed classification in the social sciences. Loads through Transformers with trust_remote_code or the social-jev package with a vLLM backend, returning a choice and probabilities per query.
Jev Models & Reimplementations#open-models#classification#python
Community
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.
Jev Models & Reimplementations#open-models#arxiv#calibration
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
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.