Jev directory
CommunityJev Models & Reimplementations
Lev — franckverrot
Open Jev-style decision model built on LiquidAI's LFM2.5-350M backbone, a clone of kev. Serves the System One API contract so the TypeSafe SDK works against a local server, returning probabilities for typed questions from one forward pass.
- Stars
- 11
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Lev — abhinavexists.
Highlights
- Open Jev-style decision model built on LiquidAI's LFM2.5-350M backbone, a clone of kev.
- Serves the System One API contract so the TypeSafe SDK works against a local server with a base_url change.
- Returns probabilities for every option of every typed question from a single forward pass; no text generation.
- Supports noul, choice (1-255 options), and score (2-255 ordered levels) question types.
- First start downloads a 25 MB adapter and the 710 MB LFM2.5-350M model.
Questions about this entry
Short answers drawn from the linked project or page.
Requires Python 3.12+, uv, and Node 20+ for the playground. Clone the repo, run uv sync --extra serve, then uv run --extra serve python -m lev.serve --run franckverrot/lev-350m --port 8009.
It supports noul with optional true/false descriptions, choice with 1 to 255 options, and score with a list of 2 to 255 ordered levels. Each question has a type, instructions, and criteria.
The first start downloads the adapter (25 MB) and LFM2.5-350M (710 MB). The server then exposes POST /v1/systemone on the chosen port, such as 8009.
Yes. lev follows TypeSafe's System One API contract, so the typesafe-sdk works against a local lev server with a base_url change, using an api_key such as local and model lev-latest.
Probabilities are served with the checkpoint's calibration temperature from calibration.json next to the weights. GET /v1/models reports it, and LEV_TEMPERATURE=1 sets the temperature to 1.
Besides POST /v1/systemone, lev exposes GET /v1/models, POST /v1/systemone/permute for one Choice under N option orders, POST /v1/systemone/separate for each question in its own pass, and POST /v1/trace for x-ray data.
The project describes itself as mostly a prototype and a fun weekend experiment, though more bumpy than planned. It is not an LLM and does no text generation; it returns probabilities for typed questions.
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
An independent, from-scratch reconstruction of a Jev-style decision model that never generates text: a state plus typed questions returns a probability for every option. Trained on Qwen3-0.6B and 1.7B backbones with LoRA and served through a system_one-shaped API.
Jev Models & Reimplementations#open-models#python#research
CommunityES7/JEV-from-Scratch
A native MLX runtime for Laya's open typed-decision weights: short decisions on Apple Silicon, with no generated tokens, PyTorch, or cloud API.
Jev Models & Reimplementations#community#python#open-models
Community
mizorewww/laya-mlxPython
mizorewww/laya-mlxPythonAn open-model semantic-if engine positioned as a local Jev-style decision stack, separate from the original SemIf repo but sharing the same author.
Jev Models & Reimplementations#community#python#open-models
Community
TheoLeeCJ/SemIf-OpenJevPython
TheoLeeCJ/SemIf-OpenJevPythonLaya typed decisions through Apple Core ML and the Neural Engine, with the author's speed and energy benchmarks for short decisions on an M3 Max.
Jev Models & Reimplementations#community#python#open-models
Communitymizorewww/laya-coremlPython
mizorewww/laya-coremlPythonA local yes/no decision model that speaks Jev's wire format on a laptop CPU, refusing Choice and Score until those question types ship.
Jev Models & Reimplementations#community#python#open-models
Community
feder-cr/jevC++
feder-cr/jevC++A local server that reads next-token probabilities from a fine-tuned Spark model and returns Choice, Score, and Noul answers with zero generated tokens.
Jev Models & Reimplementations#community#python#open-models
Community
Rizzo-AI-Academy/rizzo-flowPython
Rizzo-AI-Academy/rizzo-flowPythonFrom 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.