Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
docs(http-api): the concurrency row answers 503, so the Limits preamble cannot promise 413 for all eight
Adeshina Lasisibcad5fb1f76d
diff --git a/docs/http-api.md b/docs/http-api.mdindex ae46af99..67e1b35b 100644--- a/docs/http-api.md+++ b/docs/http-api.md@@ -278,7 +278,9 @@ Successful responses also carry `Server-Timing: inference;dur=<ms>` and `X-Infer## LimitsRequest guardrails are checked before tokenization, so an oversized request costs the server-nothing but the bytes it read. Every one of them is a `413`; the `detail` says which limit was hit.+nothing but the bytes it read. Every size limit below is a `413`; the `detail` says which limit was+hit. The last row is the exception: the concurrency cap is an admission limit, not a size one, and+it answers `503` with `Retry-After: 1`.| limit | value ||---|---|@@ -289,7 +291,7 @@ nothing but the bytes it read. Every one of them is a `413`; the `detail` says w| options per `choice` question | 100 || levels per `score` question | 32 || options across all questions | 512 |-| concurrent admitted requests | `LAYA_MAX_CONCURRENT` (16) |+| concurrent admitted requests (`503`, not `413`) | `LAYA_MAX_CONCURRENT` (16) |`/v1/systemone/batch` is bounded differently, and not by a refusal. It tokenizes each state once perquestion and collates every row into a single tensor, so the field caps multiply: 64 states of 64