Jev directory
Jev Models & Reimplementations
416 curated Jev entries. Open reimplementations of Jev, retrained heads on small models, and inference-time tricks that reproduce the System One shape with other weights.
By format
416- Repos & sites375
- Articles40
- Playgrounds1
Updated
All 416 Jev Models & Reimplementations
Search the full category, or filter by format and tag.
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 JEV decision head and rank-16 LoRA adapter for Qwen/Qwen3.5-9B, trained with AReno. Supports choice, noul, and score questions and is served through SGLang or AReno at /v1/systemone. Base weights are not included.
Jev Models & Reimplementations#open-models#local#sdk
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 380M-parameter UltraBERT encoder fine-tuned as a Jev-style decision model: it reads a state, a question, and a list of options and picks one option in a single forward pass. Apache-2.0 weights hosted on Hugging Face, scored by softmax over each option's " yes" logit.
Jev Models & Reimplementations#open-models#python#classification
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
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
A Hugging Face model repository for Aster-JEV-27B, a 27B-scale model whose chat template handles text, images, and video, emits tool calls in XML function blocks, and exposes selectable reasoning effort levels.
Jev Models & Reimplementations#open-models#local#agents
Community
LoRA adapter set for the Jevvideo long-video frame-selection agent, trained on 8xH200 from OmniJev/OneJev-4B. Ships controller, grounding, and verifier adapters plus per-role metrics and five-benchmark results.
Jev Models & Reimplementations#open-models#video#benchmark
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
Hugging Face dataset of 1,245,391 synthetic decision-modelling examples carrying Jev teacher probability distributions, used for Claes training. Access is gated and requires manual approval of the repository conditions.
Jev Models & Reimplementations#open-models#calibration#evaluation
Community
Open-weight eligibility scorer that LoRA-adapts Qwen models with a pointer head to score natural-language answer options in one forward pass, trained on TREC Clinical Trials 2021 and evaluated on 6,975 pairs from 50 unseen synthetic patients.
Jev Models & ReimplementationsArticle#arxiv#open-models#evaluation
Community
A LoRA adapter for Qwen3-Omni-30B-A3B-Instruct that scores a therapist's spoken response on the eight Facilitative Interpersonal Skills items, returning a 1-5 distribution and expected value per item from video, audio, and transcript in one forward pass.
Jev Models & Reimplementations#huggingface#calibration#evaluation
Community
A LoRA adapter for JEV-9B-MLX-NVFP4 that judges the shell commands an AI coding agent wants to run and decides whether each one can execute without asking the user. It is the local judge behind the omp command gate in Quentin-M/harness.
Jev Models & Reimplementations#open-models#security#guardrails
Community
A Hugging Face Space published by chaoliangUNSW under the slug jev-style-2b-v4-2, titled JevStyle v4.2 · Typed Decisions. It runs on Zero GPU hardware and presents the standard App, Files, and Community tabs for visitors.
Jev Models & ReimplementationsPlayground#open-models#playground#demo
Community
A sentence-transformers retriever for ROR set point matching, distilled from OpenAlex's Jev judgments. It returns candidate ROR records for an affiliation string and is fine-tuned from intfloat/multilingual-e5-base under an MIT license.
Jev Models & Reimplementations#open-models#python#research
Community
A cross-encoder set model for ROR set point matching, distilled from OpenAlex's Jev judgments. Given an affiliation string and its candidate ROR records, it gives each candidate the probability that the string names it.
Jev Models & Reimplementations#open-models#python#classification
Community
A trained example bank for @ruvector/typesafe holding 9,993 labelled Banking77 utterances across 77 banking intents with frozen split assignments. Heads and temperature calibration are refit from the bank on load; no weights are stored.
Jev Models & Reimplementations#open-models#classification#local
Community
Trained example bank for @ruvector/typesafe on the HWU64 dataset: 64 home-assistant intents across 21 domains, distributed as bank.json and questions.json with frozen split assignments rather than model weights.
Jev Models & Reimplementations#open-models#classification#local
Community
A MiniMind-JEV ranking head post-trained to pick moves in Spot's Biscuit Snake. The game offers the safe moves and the model ranks them, copying a teacher that keeps the most open room. Ships head.safetensors, a frozen BGE encoder, metrics files and a local serve script under MIT.
Jev Models & Reimplementations#open-models#games#python
Community
Ready-made Cascadia decision tree that serves autotrust/JEV-27B from OpenVINO int8 weights split into two pipeline stages. Grafts JEV-27B's verbalizer LoRA onto Intel's int8 Qwen3.8-27B IR so /v1/decisions and /v1/systemone run without the exporter.
Jev Models & Reimplementations#open-models#local#calibration
Community
Ready-made Cascadia decision tree for autotrust/JEV-9B in OpenVINO int8, packaged as a single stage of about 8.7 GB. Grafts the verbalizer LoRA onto Intel's int8 Qwen3.5-9B IR so one box can serve /v1/decisions and /v1/systemone.
Jev Models & Reimplementations#open-models#local#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
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.
Jev Models & Reimplementations#open-models#classification#local
Community
MLX precision variants of Jev-Style-2B-Decision-v4.2, a 1.88B-parameter text-only decision model for Apple silicon. Ships bf16 and 8-bit weights with a custom runtime that returns a probability for every supplied option.
Jev Models & Reimplementations#open-models#local#python
Community
arXiv paper introducing Drex, a family of four open decision models at 8B, 9B, 35B with 3B active, and 27B parameters. Reports 67.52 on Decision Index 0.4.1 versus 60.70 for Jev 1.14.0.
Jev Models & ReimplementationsArticle#arxiv#open-models#benchmark
Community
Hugging Face dataset from IntelligenceLab holding 100K-1M GUI-agent decision samples for Jev-style models. Each row pairs screenshots with a goal state, a multiple-choice question, an answer index, and metadata such as action types, horizon, and negative-plan recipes.
Jev Models & Reimplementations#agents#open-models#classification
Community
Hugging Face dataset of Gentzen LJ proof traces for intuitionistic logic, with per-step sequents, rules, pivots, and target values. Rows also carry tokenized input_ids and token_length, giving step-level supervision for decision models.
Jev Models & Reimplementations#logicrw#classification#research
Community
arXiv paper proposing TimesJev, a time series System 1 model in Jev's instant-decision shape. It formalizes System 1 sufficiency and learns a compressed representation preserving key frequency patterns, reporting over 62% better results and 62.9% less inference time than fine-tuned reasoning models.
Jev Models & ReimplementationsArticle#arxiv#research#benchmark
Community
Zuse is a family of three decision models (4B, 9B, 27B) that train a low-rank adapter and pointer head on frozen open-weight bases for 27 European languages. The 27B model reaches 87.5% accuracy with pooled expected calibration error of 0.016 on an 11-source European suite.
Jev Models & ReimplementationsArticle#arxiv#open-models#calibration
Community
A Hugging Face bundle that ports AutoTrust AI's JEV-27B to Apple's Core AI framework, with a Swift command-line runner for typed yes/no, multiple-choice, and rating decisions on Apple silicon Macs.
Jev Models & Reimplementations#open-models#local#apple-silicon
Community
arXiv paper introducing ReListen, a training-free method in which a frozen audio language model runs a Jev-style scan: it scores each 20-second window by the probability it helps answer a question, then answers from the highest-scoring minute of hour-long recordings.
Jev Models & ReimplementationsArticle#arxiv#research#benchmark
Community
Fine-tuning method that turns fix commits into comparison groups so an open-weight model scores code functions for vulnerability. An ensemble of five Qwen3.5-4B models reaches 0.814 AUROC on a 7,270-function benchmark, against 0.743 for Jev 1.13.
Jev Models & ReimplementationsArticle#arxiv#open-models#security
Community
arXiv paper introducing Kev-Bio, a vision-language model that answers clinical measurement questions to place ultrasound calipers. It turns language-model decision representations into queries matched against dense ultrasound features, producing spatial probability maps for landmark coordinates.
Jev Models & ReimplementationsArticle#arxiv#research#open-models
Community
Hugging Face dataset of synthetic conversational question-and-answer pairs about Jev internals, covering pointer-head scoring, replay-source counts, slot-selection ladders, and model lineage. English text, 10K-100K rows, Apache-2.0, tagged for fine-tuning and knowledge injection.
Jev Models & Reimplementations#open-models#research#evaluation
Community
LoRA adapter for Qwen3.5-4B that scores medical multiple-choice options in a single forward pass and returns a short JSON object with the chosen answer key and per-option probabilities, without explanations or chain-of-thought.
Jev Models & Reimplementations#open-models#python#classification
Community
Hugging Face repository holding three project-authored technical-smoke checkpoints for Active-Med-Jev, produced with the technical-smoke option on randomly generated synthetic tensors. They are software tests, not scientific or clinical models.
Jev Models & Reimplementations#open-models#community
Community
arXiv paper introducing Flide, an exact inference engine for decision models such as Jev. It decouples the logical tree of a decision request from physical execution and reports answers up to 9.5 times faster than vLLM and SGLang.
Jev Models & ReimplementationsArticle#arxiv#benchmark#evaluation
Community
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
Apache-2.0 Hugging Face repository for RSI-JEV-27b, a 27B multimodal decision model based on Qwen3.8-27B that answers supplied multiple-choice questions over images, returning a selected option and probabilities for all options in one forward pass.
Jev Models & Reimplementations#open-models#benchmark#calibration
Community
Hugging Face model card for JEV-Computer-Use, a System-One decision model for computer and browser use that reads out calibrated discrete action probabilities in a single forward pass instead of verbose text reasoning.
Jev Models & Reimplementations#open-models#browser#agents
Community
Hugging Face model repository from nikolaus714 distributing a Jev vision model in GGUF format. Its chat template accepts image and video content blocks, wrapping them in vision start and end tokens for multimodal prompts.
Jev Models & Reimplementations#open-models#local#catalog-import
Community
Satirical Python script that answers a query with DO or DO_NOT plus a random confidence percentage, presented as a natural alternative to Jev. MIT-licensed, Python 3.8+, one dependency, no API keys or model weights.
Jev Models & Reimplementations#github#python#open-models
CommunityAhmad170412/Koin
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
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.
Jev Models & Reimplementations#open-models#lora#qwen3
Community
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
Index of all 416 entries
- V Jev 1.4
- AReno-Jev-9B
- Femto Jev
- SocialJev 1.7B Preview
- SocialJev 4B Preview
- UltraBERT Jev 380M (sigmoid-norm)
- UltraBERT-Jev 380M Softmax Yes
- UltraBERT Jev 380M Softmax Yes/No
- UltraBERT Jev 380M (sqrt-softplus)
- Aster-JEV-27B
- Jevvideo OneJev-4B H200 LoRA Adapters
- N-Q-26M-JEV-1110
- syvai/jev-dataset
- TrialJev
- FIS-Jev
- Jev 9B Ft V3
- JevStyle v4.2 · Typed Decisions
- ROR Set Point Retriever E5 Base (OpenAlex Jev Distill)
- ROR Set Point Set Model mmBERT Base (OpenAlex Jev Distill)
- ruvector-typesafe Banking77 Bank
- ruvector-typesafe HWU64 Bank
- Spot Snake MiniMind-JEV v0.1
- Cascadia JEV-27B Decision Tree (OpenVINO int8)
- Cascadia JEV-9B Decision Tree (OpenVINO int8)
- EDU-Jev: Training System-One Decision Models for Education
- Jev Spam Decision 2B
- Jev-Style-2B-Decision-v4.2-MLX
- Towards Foundation Decision Models: Drex
- Jev GUI Training Preview
- Sagicc/nanoGentzen-Jev
- TimesJev
- Zuse: A Decision Model for European Languages
- JEV-27B for Core AI
- ReListen: Training-Free Evidence Localization in Hour-Long Audio
- Cyber-JEV: Matched Contrastive Fine-Tuning for Source-Code Vulnerability Triage
- Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry
- Jev History Corpus
- Medical Jev 4B
- Active-Med-Jev Technical Smoke Checkpoints
- Flide: Accelerating Decision Inference with Exact State Forking
- Medical Jev 4B Full
- RSI-JEV-27b
- JEV-Computer-Use
- Jev Vision 2B GGUF
- Koin
- Ru-Jev v1
- WorkMagic Jev Decision Qwen3 8B SFT v1
- Workmagic Jev Decision Qwen3 8B Sft V2
- LLM As Jev
- RoboJev: An Open Vision-Language Judge for Robot Success Detection
- Jev-Style 2B Decision v4 — ONNX / WebGPU
- Ling-3.0-tiny-JEV
- Naluri-561M-jev-distilled
- ruvector-typesafe CLINC150 Bank
- Darkstar JEV 27B Decision ModelOpt W4A4 NVFP4 Mixed FP8
- JEV Train Dataset (SII-liyang2024)
- JevRec: Linguistic Encoding with Jev-like Decision Modeling for LLM-based Generative Recommendation
- MiniCPM-OCR-Jev-mxfp8
- N-Q-26M-JEV-1027
- Qwen3.5-4B-Jev-Judge
- Solar-Decision-JEV-27B-V3-NVFP4-FP8
- TechnoBaptist/MiniCPM-OCR-Jev
- Jev Boost re6-hover-averitec Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev Boost re6-hover-redocred Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev Boost re6-hover-timeqa Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev Boost re7-bright-mmbright Embeddings
- Jev Boost re8 HoVer Train Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev Boost to6 AirDialogue when2call Qwen3.6-35B-A3B-FP8 Embeddings
- Jev Boost to6 fbtod when2call Qwen3.6-35B-A3B-FP8 Embeddings
- Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models
- nanoGentzen-Jev-v3
- Seeing the Options: Typed Decisions over Visual Candidates with Reusable Option Memory
- Improving JEV Entailment Reranking with Span Readouts and Selective Adaptation
- Jev Boost to6 Leyzer Home Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev Boost: To6-Presto-When2Call Qwen3.6-35B-A3B-FP8 Embeddings
- Jev Boost to7 ToolRetTrain ToolRet Qwen3.6-35B-A3B-FP8 Embeddings
- Jev-Style-2B-Decision-v4-GGUF
- Jev-Style-2B-Decision-v4-MLX
- CLM-35B-A3B Jev Boost Head
- Jev Boost to7-w2ctrain-when2call Qwen3.6-35B-A3B-FP8 Embeddings
- Jev Boost to8 abtrain apibank Qwen3.6-35B-A3B-FP8 Embeddings
- N-Q-26M-JEV
- Qwen3-ASR-0.6B-Jev-Dutch
- RetiJev
- Jev-DLC: Decision-Level Continual Learning from Typed Feedback
- Kieve-JeV Fractal 300M
- Kieve-JeV MoE 300M
- Jev Arts & Human Taste Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev Knowledge Qwen3.6-35B-A3B-FP8 Embeddings (256k)
- Jev Language Understanding Embeddings (Qwen3.6-35B-A3B-FP8)
- Jev NLI Qwen3.6-35B-A3B-FP8 Embeddings (256k)
- Jev Retrieval Qwen3.6 35B A3b Fp8 Embeddings 256K
- JEV from Scratch
- Jev-RS
- Mini-Jev — abirshhishirroy
- Lev — franckverrot
- Soro-Kev-4B
- Train-Jev 27B LoRA
- Train-Jev 4B LoRA
- Phishing Spam Jev-Like Classifier
- OSS Jev Qwen05 Decision
- PPLX Decider Flash v1.2
- SocialJev 0.6B Preview
- AutoTrust JEV-35B GGUF
- JEV-9B Core AI W8A16
- Ara-Jev-Faisal GGUF
- S1 LLM Auto-Router
- Laya Coding Decider v2
- PPLX Decider v1.2
- Kev-4B MLX FP16
- Bonsai-JEV
- Decider-0.8B Q8 GGUF
- Laya Typed-Decisions Fine-Tune
- JEV-35B AWQ INT4 W4A8
- JEV-27B-VL AWQ INT4 W4A8
- Turnike-JEV-9B Merged
- Turnike-JEV-9B
- Kev-27B Artemis GGUF
- Turnike-JEV-4B Merged
- Turnike-JEV-4B
- Ministral 3 3B Reasoning Typed Decisions
- Super-Decider
- WorkMagic Jev Churn Distill Qwen3-8B v1
- Connect AI Company v2 (RL Decider Teacher)
- Jev-Style-0.8B-Decision-v3 MLX 8-bit
- Humor-Decider-2B
- Wolf Defender Jev
- Jev-Chess 1 Small 6.5M
- Robo-Jev 2B
- Laya FullFT Typed Decisions
- Kev-4B Artemis GGUF
- Kev-9B Artemis GGUF
- Torchcast Decision 4B
- J33-Jev
- StartLux-Decision v1.1 9B Instant GGUF
- StartLux-Decision v1.1 2B Instant GGUF
- StartLux-Decision v1.1 0.8B Instant GGUF
- StartLux-Decision v1.1 27B AutoThink
- StartLux-Decision v1.1 4B Instant
- Strands-Decider 2B Qwen3.5 v1 2610
- Strands-Decider E4B Gemma4 v1 2610
- Strands-Decider E2B Gemma4 v1 2610
- Standard One 3B SH
- edceleste-decider 0.8B GGUF
- Decider-31b
- Standard One 8B SH
- Strands-Decider 2B Hobson v21
- PPLX Decider v1.1 27B
- Gemma 4 12B Unified System One GGUF
- Torchcast Decision 27B
- Jev Decisions v2 Model
- Jev Decisions v1 Model
- PPLX Decider v1 27B EXL3
- FRIDA-Decisions
- Torchcast Decision 12B
- StartLux-Decision 35B-A3B GGUF
- Strands-Decider 2B Hobson v19 ONNX
- PPLX Decider v1 27B
- StartLux-Decision v1 35B-A3B
- OpenThai-SystemOne Ollama
- Bekko System One v0 68M
- Bekko System One v0 17M
- Decision 2.0 Lux 9B
- Decision-2.0-Nox-4B
- StartLux-Decision v1 27B
- StartLux-Decision v1 27B Q8_0 GGUF
- StartLux-Decision v1 9B Q8_0 GGUF
- Decision-2.0-Kai-0.6B
- Decision-2.0-Sol-2B
- Decision-2.0-Eos-0.8B
- Intern-Decision-4B
- Intern-Decision-0.8B
- Intern-Decision-2B
- Standard One 3B
- Standard One 8B
- Standard One 3B LoRA
- Standard One 8B LoRA
- GLiNER2.5-multi-Decide
- Kev-27B
- GLiNER2.5-Decide Core ML
- GLiNER2.5-Decide-1B
- GLiNER2.5-Decide
- Decider 4B
- Decision-1.0-Nox-4B
- Kev-9B
- Kev-0.8B
- Kev-4B
- Kev-8B
- Kev-0.6B
- Decider 0.8B
- Kev-0.5B
- Decider 2B Vision
- Strands Decider
- OmniJev (tinnel123666888)
- Jiwo
- DriveJev
- Jeva — liqiiiii
- OpenJev — alanhuangyoo
- Sarvam Jev
- Lev — abhinavexists
- Chinese Decision
- Train Jev
- Agr
- Robo Jev
- Super Decider
- JevAlt
- Canopy-Jev 27B
- Jeva — chemany
- SystemOne-ONNX
- Jeff Guard Multilang
- Jev Nano
- Skycmd
- system-one (sahasrarjn)
- AgriJev: Efficient Agricultural Candidate Scoring with Multi-Scale Adapted Models (arXiv 2610.19478)
- Clef Flash on Ollama
- Laya on Ollama
- Nimble on Ollama
- Tev1 on Ollama
- MiniCPM5-2B-Jev on Ollama
- Spark-S1 on Ollama
- JEV-35B on ModelScope
- JEV-9B on ModelScope
- JEV-27B-VL on ModelScope
- Laya on ModelScope
- Laya Typed-Decisions on ModelScope
- NanoJev on ModelScope
- Jev-Omni on Replicate
- Blitz on Replicate
- Saina Helm 0.8B on Replicate
- Decidealot on Docker Hub
- OpenJev on Docker Hub
- Drex 2.0 on Fireworks AI
- SubQ Snap
- Imajev 4B
- PurpleMIST-Flash-1.0
- PolicyLM-1.7B
- Bespoke-Nimble-9B-v3
- Vega 0.8B: public intents
- Phocinae-Largha-150M-v1
- VideoJev
- Laya Vision
- Rev
- Visual Jev
- Sokudan (即断)
- Decima
- Dex
- openjev on Qwen3.5
- Clef on Hugging Face
- Jeff 1
- Decider 2B
- JEV-CPU — huggingface.co
- Open-Jev-9B
- APUS-OpenJev (APUS Reflex)
- Eikos-27B
- Laya Browser
- THX-01
- Laya Vision (201M checkpoint)
- Jev Lite
- Ollaya Models
- Strands Decider 2B — strandsagents.com
- Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees (arXiv 2610.18326)
- SecJev: Bringing Security Expertise to System One Decision Models (arXiv 2610.03073)
- Jeva: System One Models from First Principles (arXiv 2610.18773)
- JevGPT: Thinking Fast and Slow in Autonomous Research (arXiv 2610.18272)
- Releasing the Inner Jev: A Simple Recipe for Open Decision Models (arXiv 2610.17205)
- OpenJev-RLCD: A Working RLCD Implementation (arXiv 2609.38850)
- Chinese-Jev: Bringing System One Model to Chinese-Language Tasks (arXiv 2609.36965)
- From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model (arXiv 2609.29283)
- NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees (arXiv 2609.28587)
- Visual Jev: Accurate and Efficient Decisions from Shared Visual Context (arXiv 2609.25845)
- VideoJev: System One Model for Video Understanding and Interaction (arXiv 2610.18615)
- FunDM: Cheap & Label-Free Decision Models from Frozen Language Models (arXiv 2610.17175)
- AnyJev Technical Report (arXiv 2610.00831)
- Calibrated Typed Decisions for Entity, Relation, and Event Extraction (arXiv 2610.17113)
- SanSi: A Looped Typed Decision Model for System 1.5 Thinking (arXiv 2610.07730)
- From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders (arXiv 2610.02486)
- StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions (arXiv 2610.17309)
- OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One (arXiv 2610.00381)
- NavJev: Efficient Vision-Language Navigation via Action-Centric Visual Compression and Discriminative Action-Semantic Memory (arXiv 2609.34969)
- LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information (arXiv 2609.30706)
- AutoTrust JEV-35B
- AutoTrust JEV-Gemma4-26B-A4B
- Jev-Omni
- Jev-Omni Q4_K_M GGUF
- Jev-Omni MLX 4-bit
- JevK5 — huggingface.co
- JevK5-9B
- Jev-Style Qwen3.5-2B GGUF
- Jev-Style Qwen3.5-2B MLX
- Jev-Style 2B Decision v3 GGUF
- open-jev DeBERTa-v3-large
- open-jev DeBERTa ONNX
- NeoHorse-Jev-4B
- DepGuard Jev-Style 1.5B
- Jev-alpha-26B-A4B
- Bit Jev 2B Distilled
- Visual Jev 4B
- mini-Jev — huggingface.co
- W1-JEV
- ModernBERT-ja 310M Jev
- Tiny-Jev
- AgentJev-0.6B — huggingface.co
- JevEmbed Qwen3 Embedding 0.6B
- Laya Multilingual
- Laya Typed-Decisions GGUF
- EmbeddingGemma 2 Typed Decisions
- Gemma 3 270M Typed Decisions
- OCF Typed-Decisions Smoke
- OpenThai-SystemOne
- OpenThai-SystemOne Core AI
- systemone-lite 0.5B
- System One Scorer
- Kenning-XL v0.6
- System One Zeroshot
- Bekko System One v0 400M
- StartLux-Decision v1 4B
- Lavoir
- Train your own decision model with Unsloth
- Cloudflare Clef
- Clef-omni
- Liquid AI d1
- Laya on Hugging Face
- Laya Typed-Decisions
- Julia 1
- Julia 1 WebGPU
- AutoTrust JEV-27B
- AutoTrust JEV-27B-VL
- AutoTrust JEV-9B
- AutoTrust GEV-26B-Decide
- Liquid AI d1-3B
- Decider Chat Gemma-4-31B
- Jev-Style 0.8B Decision v3 GGUF
- Interfaze Lev
- Drex DLM
- OpenDecider Nano
- Decision 2.0 Vega
- Security-One 27B
- Darwin-27B-ZTC
- Strands Decider 2B — huggingface.co
- Gero-4B
- Cua-S1 Forms
- bev-decider 0.4B
- Archai Jev Zagreus 0.4B Italian
- Jev-MedQA
- WaterSheep
- laya-Ascend
- Djev Run
- Visual-Jev
- WebJev
- Gutsy
- Sezika
- RSI-Jev
- Bespoke Nimble
- Jebadiah
- Bud Decision Studio
- Ruling
- AutoJev — denis-pplx
- Qwev
- Jevlike Esp32
- Bekko System One
- Jag
- Luce
- Intern Decision Mlx
- OmniJev — shapsider
- Vev
- Laya-MLX
- Laya-CoreML
- Together: train your own Jev for $17
- System One Foundation Models
- Gut — Kungie
- Kev Onnx
- Laya Jev Compatible Server
- Klint
- Laya System One
- ComfyUI-ScriptFlow
- Pilot Typesafeai Jev
- JevNext
- Open Jevlike Infer
- Dlm Jev
- Jev Demo — julianoczkowski
- Sys1rust
- Scheda.js
- Openthai Systemone Doom
- Minicpm5 2B Jev
- ifReflex.cpp
- Systemone — codesoda
- Longjev
- Laya Pi
- Local Issue Classifier
- Jevons
- Codriver
- Simple-Jev
- Apply OS
- LocalJev
- SemIf-OpenJev
- Jeeves
- NeoHorse
- Jeff — firelex
- Deepopen
- Intern-Decision
- Open-Jev — Zefan-Cai
- Djev Spark
- Imajev
- Laya Ultrafast
- CLM
- OpenJev — SiliconLabAI
- Jevper
- Jevos
- Ollaya
- Rizzo Flow
- Lichen
- Verdict — khimaros
- Valen
- OpenDecision — deepanwadhwa
- Decis
- mini-Jev — r-ms
Start here with the Jev AI model
Featured entries in models & reimplementations.
AutoTrust's bf16 System 1 decision model on Qwen3.5-35B-A3B with about 3B active parameters: Decision Index 0.3 public 59.73, ERQA 51.3% in one pass with zero robot training, 66.5 GiB of weights.
Jev Models & Reimplementations#community#open-models#local
Community
The Hugging Face hub for Laya's open System 1 checkpoints: the 421M English model at the repo root, a 322M multilingual build in a subfolder, and the typed-decisions fine-tune, all Apache-2.0.
Jev Models & Reimplementations#community#open-models#local
Community
The vision sibling: the same text-trained System 1 head on Qwen3.8-27B's image encoder, taking images zero-shot, ranked first of 20 vision decision models on the community Jev Decision Index 0.3.
Jev Models & Reimplementations#community#open-models#local
Community
Jev AI model articles
Original guides that go deeper on Jev models & reimplementations.
Pointer heads, slot heads, and frozen backbones: how open decision models are trained, what the adapters change, and what the cards leave out.
Jev Models & Reimplementations#models#training#open-models
Read article
Weights are one artifact; license, provenance, calibration, and maintenance are separate. What to verify before an open checkpoint reaches production.
Jev Models & Reimplementations#models#licensing#open-source
Read article
A router is a decision model with a different job. How to cascade rules, small models, and humans without turning the agent into a chain of calls.
Jev Models & Reimplementations#models#routing#agents
Read article
From the Jev community
Watch walkthroughs, read the threads, and see what builders are posting.
YouTube: Nate Herk compares speed and cost against ordinary models, then builds an X feed classifier and a paper-trading prototype.
YouTube: Ray Amjad puts Jev inside an agentic coding loop and looks at what it costs to run.
YouTube: David Ondrej explains the architecture behind Jev and how to build a business on it.
Hacker News: Nikola Balić on what made the Jev launch easy to try and easy to share.
nkko2 pointsWhat TypeSafe Got Right with the Jev LaunchRead 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 NewsHacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.
2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker NewsHacker News: Thread on Selmar's Jev code-review calibration notes and ordering.py comparisons.
Lectem2 pointsCalibrating Jev as a Code ReviewerRead the thread on Hacker News