A candidate-scoring head returns distributions for gates, routes and scores without decoding prose or JSON answers. The README compares a benchmark-trained AgentJev specialist with Jev 1.13.0 evaluated zero-shot; these use different training conditions.
jev-lm: A word-level language model whose output layer
y0usaf/jev-lm
VerifiedResearchDocumented
jev-lm (y0usaf): A word-level language model whose output layer is Jev. Explore the Jev references, TypeScript source code and similar projects.
Repository description: A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval
What you can build with it
Get started
Clone the repository and follow its README for install and usage. JevHunt has not run this project.
git clone https://github.com/y0usaf/jev-lm.gitProject facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- TypeScript
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-16
- Last code update
- 2026-09-16
- GitHub stars
- 7
- Evidence checked
- Sep 30, 2026
- Metadata checked
- Sep 30, 2026
- Check status
- Up to date
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
Set a key one of three ways: `TYPESAFE_API_KEY`, a file named by `TYPESAFE_API_KEY_FILE`,
Evidence commit: fb4123e36bf8dd1a21748a00974442b710c7f945
Discovered through: awesome-jev.
How we review →Suggest a correction · Claim this listing · Submit a project