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 1024-budget ceiling for the short label is 339, not 338
Nandakishord4f5740c3d77
diff --git a/docs/http-api.md b/docs/http-api.mdindex 48e2721a..d8975625 100644--- a/docs/http-api.md+++ b/docs/http-api.md@@ -382,7 +382,7 @@ naming only `head_max_len` "pointed at the wrong knob in both directions".How many options fit at all is set by that same pair *and* by their text. With no description on theoptions, at `max_len=512` and `head_max_len=192` the largest single choice question that is notrefused carries 168 options when each label is `T <i>` and 126 when each is-`Tickets routed to queue <i>`; at `max_len=1024` those become 338 and 254. Each of those four+`Tickets routed to queue <i>`; at `max_len=1024` those become 339 and 254. Each of those fourboundaries was met through the public call: it answers at the ceiling and refuses one option aboveit. Those 126 sentence labels carry a second lesson -- the answered call reports`options: {"q": {"total": 126, "distinct": 1, "tokens_per_option": 4}}`, because the 4-token cap left