DEDUPEDWhat do you want to do?
3 use cases
-
Run the bundled demo to see typed readouts in action
Clone the repo, install PyTorch, and run the demo to see Noul, Choice, and Score answers on sample state.
View prompt
Clone https://github.com/kyegomez/open-jev, install torch>=2.0, and run python open_jev/main.py. Report the printed answers for the wants_refund, route, and frustration questions. Verify that the route answer is exactly one of billing, technical, or account.
-
Prototype typed yes/no, choice, and score questions over JSON state
Write your own nested state and declare Noul, Choice, and Score questions to test how the typed readouts behave.
View prompt
Using the repo at https://github.com/kyegomez/open-jev, write a script that builds a state dictionary from <your record file>, declares one Noul, one Choice, and one Score question, and prints the answers. Expected output is one typed answer per question; verify that every Choice answer is one of the declared options.
-
Test soft-target training with RLCDLoss on your own labels
Use probability distributions as targets and run one loss and backward step to study the calibration-oriented objective.
View prompt
In the repo https://github.com/kyegomez/open-jev, build soft probability targets for <your question set> and compute RLCDLoss on the model with one backward pass. Expected output is a scalar loss tensor with gradients; verify that each target row sums to 1 before calling the loss.
How to use Open Jev
- Check you have what it needs: Python 3.10 or newer (recommended in the README); git installed; PyTorch 2.0 or newer.
- Open kyegomez/open-jev on GitHub and read the README and license.
- Clone the repository:
git clone https://github.com/kyegomez/open-jev - Enter the project folder:
cd open-jev - Install the dependency:
python -m pip install "torch>=2.0" - Run the full demo:
python open_jev/main.py
These steps come from our top use case, Run the bundled demo to see typed readouts in action, which also has a copy-paste agent prompt.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forWritten for ML engineers and researchers who want to study a typed, non-generative readout architecture, not for teams that need a working production model.
- Why it is hot
- LanguagePython
- Sourcegithub.com/kyegomez/open-jev · Back to Hot repos
Requirements
- Python 3.10 or newer (recommended in the README)
- git installed
- PyTorch 2.0 or newer
- Basic familiarity with running Python scripts from a terminal
Maintain Open Jev? Add the Featured on Deduped badge
Paste this into your README:
[](https://dedupedai.com/use-cases/kyegomez-open-jev/?ref=badge)
Questions about Open Jev
What is Open Jev?
Open Jev is an untrained PyTorch research reconstruction of the ideas behind TypeSafe AI's Jev, which answers typed questions about nested state without generating text. It is an open-source project on GitHub: https://github.com/kyegomez/open-jev.
Who is Open Jev for?
Written for ML engineers and researchers who want to study a typed, non-generative readout architecture, not for teams that need a working production model.
What can I do with Open Jev?
3 use cases so far, for example: Run the bundled demo to see typed readouts in action; Prototype typed yes/no, choice, and score questions over JSON state; Test soft-target training with RLCDLoss on your own labels. Each has steps and a copy-paste agent prompt.
What do I need to run Open Jev?
Python 3.10 or newer (recommended in the README); git installed; PyTorch 2.0 or newer; Basic familiarity with running Python scripts from a terminal.
What are alternatives to Open Jev?
Other hot AI repos in Research: Scientific Agent Skills, Speaker Mem R1, DSH Council, Evo Bot, AI Engineering Course.
Is Open Jev safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.