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
Merge pull request #759 from NAVEENPRASAATH23/feat/evals-onnx-calibration
Nandakishor1389f7003c1e
diff --cc laya/evals_cli.pyindex dcb9d33a,c63b0a99..5882b3dd--- a/laya/evals_cli.py+++ b/laya/evals_cli.py@@@ -303,10 -299,10 +307,12 @@@ def _cmd_run(args) -> int# refetched under the same name, and a reviewer comparing two reports needs the# report -- not a file mtime -- to say so."dataset_sha256": evals.file_fingerprint(args.dataset)}+ if policy:+ config["gate_policy"] = policyif args.onnx:config["onnx"] = args.onnx+ if args.calibration:+ config["calibration"] = args.calibrationif extra:config["score_within"] = [evaluator.tolerance for evaluator in extra]report = evals.evaluate(runner, dataset, evaluators=evals.default_evaluators() + extra,