Jev-Style
Local toolkit to classify text, route requests, and score options with probabilities.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
Python 3.10 or newer
Install jev-style torch backend
pip install -U "jev-style[torch]"
Check that it works
jev-style --versionThe output should contain “0.6.2”.
First thing to try
jev-style serve --fakecurl -s http://127.0.0.1:8765/healthz && echo "---MODELS---" && curl -s http://127.0.0.1:8765/v1/modelsStart the local server with jev-style serve, then send requests to it from another terminal.
What it does
- Classify text and get a probability for each optionTested
How to use it
- Start the server with
jev-style serve --fake. - Run
jev-style decide "<your text>" --url http://127.0.0.1:8765 --choice "<question>::<option1>,<option2>,<option3>". - Read the probability for each option in the
probabilitiesfield of the output.
- Start the server with
- Route support tickets and requestsNot tested
- Review receipts and screenshots from imagesNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 1 of 3 features work
- Works offline
Good for
- route support tickets
- decide when to call a larger model
- review receipts or screenshots with image-capable build
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its service answers requests
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 0.6.2
Differences the test machine hit
- README: pip install -U jev-style[mlx] as first candidate
In the test: On Linux x86_64 use pip install "jev-style[torch]"; mlx backend is Apple-silicon only and cannot work here - README: jev-style serve downloads 0.8B weights (~1.5GB)
In the test: jev-style serve --fake for deterministic answers with no 1.5GB weight download; plain serve needs download and RAM beyond 2GB box - README: review receipts or screenshots with the image-capable build
In the test: Fake server reports images:false and rejects assets with 400 images_not_supported; images need 2B v4 torch build