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(readme): list predict_tournament under the many-option limit
Rishit Sharma24aab6f91034
diff --git a/README.md b/README.mdindex 9c701422..efaba2b7 100644--- a/README.md+++ b/README.md@@ -1488,6 +1488,7 @@ failure; it does not establish calibrated confidence.1. Raise `agent.cfg["head_max_len"] = 512` and `agent.cfg["max_len"] = 1024` (or up to 2048 / 4096 / 8192) so every option has enough tokens to remain distinct. Both are also per-request: `predict(state, questions, head_max_len=512, max_len=1024)` widens one question without changing the agent for everyone else, and every LangChain node takes the same two arguments ([LangChain guide](https://github.com/NandhaKishorM/laya/blob/main/docs/langchain.md)). `laya --questions` takes the same two budgets as `--max-len` / `--head-max-len`.2. Or shortlist with embeddings and run one forward pass on the top `k` labels (`predict_shortlist`, example below). `predict` and `system_one` still score every criterion they are given.3. Or split the label set yourself into a coarse question and a fine question.+ 4. Or let the decision model narrow the set itself: `laya.predict_tournament(agent, state, questions)` answers the labels in groups of at most 16, every group in the same forward pass, then asks the question again over the group winners, so up to 256 labels take two `predict` calls and no embedder. On the full test splits with the English checkpoint it took BANKING77 (77 labels) from 0.430 to 0.610, CLINC150 (150) from 0.625 to 0.876 and MASSIVE intent (60) from 0.515 to 0.569, with ECE between 0.06 and 0.14 instead of 0.30 to 0.37, at about twice the latency of one question ([`research/benchmarks/tournament`](https://github.com/NandhaKishorM/laya/blob/main/research/benchmarks/tournament/README.md)). When the labels fit uncut in a raised budget, as MASSIVE's 60 do at `head_max_len=512`, raising it did better (0.622 against 0.590 on 500 rows). Probabilities on a tournament choice are over its finalists.```pythonimport laya