by NandhaKishorM · 未分类 · ★ 33.5k
Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request. Laya evaluates typed questions (, , ) over any state (text, email, ticket or JSON document) in a single forward pass — 33 ms for one question, 7.2 ms/question batched, measured on a T4. No text generation, so nothing to parse and nothing to hallucinate.
| Stars | 33,511 |
| Forks | 3,009 |
| Language | Python |
| Category | 未分类 |
| License | Apache-2.0 |
| Quality Score | 63.1999483515357/100 |
| Open Issues | 85 |
| Last Updated | 2026-10-19 |
| Created | 2026-09-18 |
| Platforms | python |
| Est. Tokens | ~25k |
These tools work well together with laya for enhanced workflows:
Explore other popular 未分类 tools:
laya is 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 reque. It is categorized as a 未分类 with 33.5k GitHub stars.
laya is primarily written in Python. It covers topics such as calibration, classification, decision-model.
You can find installation instructions and usage details in the laya GitHub repository at github.com/NandhaKishorM/laya. The project has 33.5k stars and 3009 forks, indicating an active community.
laya is released under the Apache-2.0 license, making it free to use and modify according to the license terms.