COMMUNITY OBSERVEDMetric claims: AUTHOR REPORTEDSOURCE AUDITED🤖 Jev Agent

Laya

Open weights that answer typed questions in one forward pass, 33 ms on a T4.

Overview & result

Nandakishor M shows Laya, built on Jev: Open weights that answer typed questions in one forward pass, 33 ms on a T4.

From the original post

Laya by @nandakishorm: Open weights that answer typed questions in one forward pass, 33 ms on a T4.

— Nandakishor M

How Jev fits in the loop

  1. Laya is an open, multilingual, non-autoregressive model installed with pip or uv.
  2. It answers typed questions in a single forward pass; the author gives 33 ms.
  3. A router picks the right checkpoint for each request.
  4. Optional extras add an HTTP server, an MCP server and LangChain integration.

How to reproduce

  1. Review the source documentation and repository at https://github.com/NandhaKishorM/laya.
  2. Configure environment with TypeSafe Jev / System One API keys.
  3. Run test prompts against the decision endpoints.

Why this build matters

Shows Jev in practical use for research and data analysis.

Limitations

  • The README's "honest limits" say the base checkpoints are near chance zero-shot on typed-decisions (0.362 and 0.352 against a 0.318 random baseline).
  • The 0.766 figure comes from a checkpoint fine-tuned on that benchmark's own training split.
  • The author describes it as a fast base to specialise, not a zero-shot decision engine, and warns against boolean-word labels in choice questions.

Patterns