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
release: 0.3.17, multilingual quickstart and fine-tuning callout
Nandakishor53e38a594566
diff --git a/README.md b/README.mdindex 31b1ad2a..ec72b63d 100644--- a/README.md+++ b/README.md@@ -53,15 +53,32 @@ print(result["answers"]["churn_risk"]["noul"]) # probability the answer is yeprint(result["routing"]["model"]) # english```-Text in any of 100+ languages works the same way: the `Router` sends it to `laya-multilingual` automatically. From the command line, `laya "My payment failed twice" --preset triage` answers a ready-made question set. More in the [full quickstart](#quickstart-route-mode-recommended) and the [docs](https://nandhakishorm.github.io/laya/).+The same call works in any of 100+ languages. The `Router` detects the script and language and sends non-English text to `laya-multilingual`:++```python+for text in ["मुझसे मार्च में दो बार शुल्क लिया गया, कृपया डुप्लिकेट राशि वापस करें।",+ "La aplicación se cierra cada vez que abro la configuración."]:+ r = router.predict(text, {"department": questions["department"]})+ print(r["routing"]["model"], r["answers"]["department"]["choice"])+# multilingual billing+# multilingual technical+```++From the command line, `laya "My payment failed twice" --preset triage` answers a ready-made question set. More in the [full quickstart](#quickstart-route-mode-recommended) and the [docs](https://nandhakishorm.github.io/laya/).++## Fine-tune for better accuracy++The shipped checkpoints work zero-shot, but fine-tuning on decisions from your own domain is where accuracy jumps. On the typed-decisions benchmark (2,000 decisions across four workflows), the fine-tuned `laya-typed-decisions` checkpoint scores **0.766** accuracy, against **0.362** for the base English checkpoint on the same decisions.++**[Fine-tuning notebook](https://github.com/NandhaKishorM/laya/blob/main/notebooks/laya_finetune_typed_decisions_2xT4_kaggle.ipynb)**: runs the whole loop on Kaggle's free 2x T4 GPUs (build the dataset, train, fit calibration temperatures, evaluate, and push the result to the Hub). Details in [Fine-Tuning](#fine-tuning).## Documentation**[nandhakishorm.github.io/laya](https://nandhakishorm.github.io/laya/)**: guides for [prediction hooks](https://nandhakishorm.github.io/laya/hooks/), [schema-driven decisions](https://nandhakishorm.github.io/laya/structured/), [Docker](https://nandhakishorm.github.io/laya/docker/) and [LangChain and LangGraph](https://nandhakishorm.github.io/laya/langchain/), plus a full [API reference](https://nandhakishorm.github.io/laya/reference/).-## What's new in 0.3.16+## What's new in 0.3.17-* **Installation, quickstart and documentation first.** This README now opens with how to install Laya, a runnable example, and where the docs are.+* **Installation, quickstart and documentation first.** This README now opens with how to install Laya, runnable English and multilingual examples, how fine-tuning improves accuracy, and where the docs are.* **Documentation site** at [nandhakishorm.github.io/laya](https://nandhakishorm.github.io/laya/), with an API reference generated from the docstrings.The code is unchanged from the last runtime release, whose fixes are:diff --git a/laya/__init__.py b/laya/__init__.pyindex 758bd2c5..d96504ab 100644--- a/laya/__init__.py+++ b/laya/__init__.py@@ -14,7 +14,7 @@ from .presets import (from .router import DEFAULT_MODELS, RouteDecision, Routerfrom .structured import DecisionResult, decide-__version__ = "0.3.16"+__version__ = "0.3.17"# Routing, language detection and email cleaning are pure Python. The torch-backed names are# resolved lazily so that `import laya` -- and therefore `from laya import Router` ordiff --git a/pyproject.toml b/pyproject.tomlindex 4ed05199..c4ab3bb6 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"[project]name = "laya"-version = "0.3.16"+version = "0.3.17"description = "Fast, non-autoregressive System 1 decision engine with calibrated probabilities"readme = "README.md"requires-python = ">=3.10"