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 option ceiling moves with the question's instructions too
Aashisha93d20b80929
diff --git a/docs/http-api.md b/docs/http-api.mdindex d8975625..2cf9a5ac 100644--- a/docs/http-api.md+++ b/docs/http-api.md@@ -379,12 +379,20 @@ raise max_len, or use fewer options`, which `max_len=1024` then answers. The meslevers because either can be the fix; `laya/agent.py::_encode_state` keeps a comment recording thatnaming 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 the-options, at `max_len=512` and `head_max_len=192` the largest single choice question that is not-refused 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 339 and 254. Each of those four-boundaries was met through the public call: it answers at the ceiling and refuses one option above-it. Those 126 sentence labels carry a second lesson -- the answered call reports+How many options fit at all is set by that same pair *and* by their text *and* by the question's own+`instructions`. With no description on the options and a three-token instruction (`Which queue?`), at+`max_len=512` and `head_max_len=192` the largest single choice question that is not refused 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 339 and 254. Each of those four boundaries was met through the public call:+it answers at the ceiling and refuses one option above it. Change the instruction and they move -- a+two-token one gives 169, 127, 339 and 255, an eight-token one gives 168, 126, 338 and 254 -- because+`laya/common.py::build_head` truncates the encoded `choice question: <instructions>` prefix to+`max(8, opt_budget)` tokens, so the first `[MASK]` lands at position 7, 8 or 10 for those three+wordings and every marker after it shifts with it. The ceiling stops moving once the instruction+reaches the cap: the same seventeen-token wording returns the eight-token numbers exactly. The state+does not move it either -- at `max_len=1024` with the eight-token instruction, 338 options answer and+339 refuse whether the state is one word or the eleven-token sentence this section has been using.+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 leftevery option the same span, so the question could not tell its 126 choices apart, and only acollision like that puts `options` in the response. Both default ceilings sit above@@ -393,8 +401,9 @@ refusal -- and reaches a budget refusal only by raising `max_len` or `head_max_lwhich is accepted up to `LAYA_MAX_TOKEN_BUDGET`, 8192 by default. (`LAYA_TOURNAMENT_GROUP` raises thecount cap to 255 but narrows those choices into groups, so they never reach the one-pass budget.) Acaller comparing this endpoint with another server's stated "maximum N options" therefore has to quote-the budget it sent and the option text, not just N. The [Evaluation harness](evals.md) runs the same-requests in-process without the HTTP layer, so there the 168/126 ceiling is the one that binds.+the budget it sent, the option text and the instruction, not just N. The [Evaluation harness](evals.md)+runs the same requests in-process without the HTTP layer, so there the 168/126 ceiling is the one that+binds.## Errors