CommunityJev Models & Reimplementations
Together: train your own Jev for $17
Together AI's tutorial for fine-tuning a Jev-like classifier, Tev1, on Qwen3.5 4B and serving it on Together. The example uses 38,340 rows.
- Format
- Article
- Published by
- Community
- Author
- Together AI
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- Together says it launched together/Tev1-4B-experimental, a Jev-like classifier on Qwen3.5 4B, on its serverless platform.
- The tutorial fine-tunes that shape on 38,340 examples and puts the cost of that run at about $17.
- It says that training run takes about twenty-five minutes, then deploys behind an HTTP endpoint.
- The post describes the result as a score, a boolean, or a multiple-choice answer from predefined questions.
Watch out
Tev1 is Together's model, not TypeSafe's hosted Jev. The $17 figure is Together's example for that dataset size.
Questions about this entry
Short answers drawn from the linked project or page.
No, it gives you the same shape on an open base. The entry copy has Together launching a Jev-like classifier of its own on an open four-billion-parameter base, and the tutorial fine-tuning that shape. Training cost says nothing about hosted quality, and the entry copy separates the two explicitly.
One example. The entry copy puts the cost at roughly that much for a run over 38,340 rows taking about twenty-five minutes, and its caveat says the number is scoped to that dataset size. Different row counts, sequence lengths or epochs move it, so do not treat it as a per-model price.
A score, a boolean, or a multiple-choice answer drawn from questions you define, which the entry copy lists as the output shape. That is the familiar decision interface on your own weights, but nothing in the post reports how well it scores.
That you now own the serving and the accuracy. The entry copy has the deploy land behind an ordinary HTTP endpoint, and the model is labeled experimental on their serverless platform. Nobody has published a comparison against the hosted product.
It works a customer-support intent classification. The sample message says the company charged a card twice for the October subscription, both $19.99 on the same day, and the multiple-choice question asks which listed support intent best matches, including a None of the listed intents matches option.
Tev1-4B-experimental is built on Qwen3.5 4B and served on Together's serverless platform. The tutorial covers fine-tuning and deploying a classification model that answers these decision-style questions rather than calling TypeSafe's hosted Jev.
It says it will cover how to fine-tune and deploy a classification model that can answer these types of questions, which is the Jev-like decision shape on Together's own open base rather than the hosted product.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
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 NewsHacker News: A one-token logprob wrapper that also classifies webcam frames.
allanrbo151 pointsA single function Jev-like wrapper for LLMs, including vision modelsRead the thread on Hacker NewsMore Jev resources like this
6.9kGitHub stars
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-mlxPython4.8kGitHub stars
An 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-OpenJevPython1.6kGitHub stars
Laya 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-coremlPython1.3kGitHub stars
A 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++823GitHub stars
A local Jev-compatible POST /v1/systemone server in TypeScript that maps typed questions onto oMLX classification prompts and normalizes logprob-style answers.
Jev Models & Reimplementations#community#typescript#local
Community
githubnext/localjevTypeScript
githubnext/localjevTypeScript1.3kGitHub stars
A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.
Jev Models & Reimplementations#community#rust#open-models
Community
ollaya-dev/ollayaRust
ollaya-dev/ollayaRustFrom the Jev guides
Original write-ups on what this entry is for.
Jev takes text only; Clef-omni adds image, audio, and video input and Liquid d1 adds images, each keeping the same typed-answer shape. Where that matters, where it does not, and the costs the vendors underplay.
Jev Models & Reimplementations#multimodal#open-models#decision-model
Read article
One model in September, a dozen by October. Clef, Liquid d1, Perplexity, and OpenAI all ship the same typed-answer shape now. How to read the rival benchmarks and pick on your own task.
Jev Models & Reimplementations#decision-model#benchmarks#pricing
Read article
Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.
Jev Models & Reimplementations#open-models#hugging-face#local
Read article
From the Jev community
Posts from builders shipping with Jev right now.