Jev directory
CommunityJev Models & Reimplementations
Jev Lite
vagmi's QLoRA adapter turns Gemma 4 E4B into a System One model: it reads the answer from the logits at the option letters, so it cannot answer outside your options, and returns choice, score and yes/no from one forward pass.
- Reading time
- 2 min
- Published by
- Community
- Author
- vagmi
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Capabilities
- Open sourceRuns locally
Highlights
- A QLoRA adapter for Gemma 4 E4B that reads answers from the logits at the option letters, per the card's summary.
- Because the answer comes from option-letter logits, the model cannot answer outside the options you supply.
- Returns choice, score and yes/no decisions from one forward pass, without generating text.
Watch out
The fetched page text on 2026-10-15 was a Gemma 4 chat-template dump, so this entry rests on the card's title and meta description. No training data, benchmark numbers, hardware requirements or licence terms were readable in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A QLoRA adapter by vagmi that turns Gemma 4 E4B into a System One style decision model. It returns choice, score and yes/no answers from one forward pass without generating text.
It reads the answer from the logits at the option letters, so it can only pick among the options you provide. That makes it impossible for the model to answer outside your declared choices.
The card's summary lists choice, score and yes/no decisions, the same typed-decision shapes as Jev, all returned from a single forward pass.
Gemma 4 E4B, adapted with QLoRA. The digest did not include training data or evaluation details because the fetched page text was a chat-template dump.
It is a downloadable adapter, so it runs wherever you can load Gemma 4 E4B. The digest did not capture hardware requirements or serving instructions.
The digest did not include licence terms for the adapter, so check the model card before using it commercially.
It is a local adapter rather than a hosted service, so probabilities come from your own hardware. The digest publishes no accuracy comparison against Jev or other open models.
More Jev resources like this
Gestalt Labs' Jeff is a LoRA adapter on Qwen3-4B-Instruct-2507 that answers Jev-style choice, noul and score questions with labels and probabilities instead of prose, runs locally, and ships a train-your-own guide; on 9,730 fact-checking examples it trails Jev 1.13.0 on accuracy (0.8183 vs 0.8283).
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
Zefan Cai's LoRA adapter and scalar decision head for Qwen3.5-9B score caller-supplied candidates for choice, yes/no and score answers without generating text, served over a local /v1/systemone endpoint.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
An open, local attempt to bring Jev-style typed decisions to images: a Qwen3-VL backbone returns numerical distributions for independent choice, score and noul questions without generating answer text.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
andrueandersoncs/visual-jevPython
andrueandersoncs/visual-jevPythonAn open-source, Jev-compatible System One model: Dex answers choice, score and yes/no questions over text in a single forward pass from an Ettin-1B encoder, and speaks the same /v1/systemone shape as Jev.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
canadaornaw/dexPython
canadaornaw/dexPythonA LoRA plus 24-slot decision head over Qwen3.8-27B from Ming Xu's train-jev project: it serves TypeSafe's System One API with 0.851 Kev transfer-v4 accuracy and ECE 0.053, and needs an 80 GB GPU.
Jev Models & Reimplementations#community#open-models#local
Community
A 24 GB-GPU alternative from the train-jev project: Qwen3.5-4B plus a rank-16 LoRA and 24-slot decision head scoring 0.647 PK accuracy, 40.4 Decision Index and 43 ms p50 latency, ahead of Kev-4B at the same size.
Jev Models & Reimplementations#community#open-models#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.