Jev directory
CommunityJev Models & Reimplementations
Cascadia JEV-9B Decision Tree (OpenVINO int8)
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.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Single-stage tree of about 8.7 GB, the exporter's default layout.
- Measured 80/82 parity against fp32, with two near-tie flips at reference margins 0.002 and 0.025.
- /v1/decisions and /v1/systemone returned identical results on 82/82 questions.
- Requires OpenVINO GenAI 2026.4.1; 2026.4.0's GPU plugin has an access violation under long generations.
- Weights are byte-identical to pawanpaudel93/jev9b-int8-ov-decision.
Questions about this entry
Short answers drawn from the linked project or page.
Download it with hf download pawanpaudel93/cascadia-jev-9b --local-dir ~/trees/cascadia-jev-9b, then run cascadia run ~/trees/cascadia-jev-9b/int8/stages-1 --engine qwen35 --device GPU --api 127.0.0.1:8080.
The int8/stages-1 preset is one stage with 32 layers and a total size of about 9.3 GB on disk, described as roughly 8.7 GB of weights for a single box.
Use OpenVINO GenAI 2026.4.1. Version 2026.4.0's GPU plugin has an access violation under long generations.
Yes. The published measurements used --device GPU on an Intel Core Ultra 7 258V with Arc 140V iGPU and 32 GB, and the same files work with --device CPU.
Over 50 records and 82 questions it scored 80/82 PASS against the streamed fp32 reference. The two differences were near-tie flips with reference margins of 0.002 and 0.025, and no confident flip occurred.
Apache-2.0, as are all inputs: the autotrust/JEV-9B fine-tune, Intel's OpenVINO/Qwen3.5-9B-int8-ov IR, the Qwen base, and the Cascadia conversion. The repository redistributes converted weights only and adds no training.
With tools/decision_export.py from the labscommunity/cascadia branch pawan/decisions-api at commit 94cfdf9b, using the int8 Qwen3.5-9B IR as base and the JEV-9B adapter directory, with the decision head reading verbalizer token logits.
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
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
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
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.