Laya open-sourced: 33ms non-autoregressive decision model with routing
duummbass · x · 2026-09-20
convaiinnovations open-sourced Laya on Hugging Face: a multilingual, non-autoregressive System 1 decision model. Given a state (text, email, ticket, or JSON) and typed questions, it returns typed answers with mathematically calibrated probabilities in a single forward pass (33 ms) across 100+ languages. It is trained with RL against strictly proper scoring rules (RLCD), so honest probability reporting is the only reward-maximizing strategy; it never generates text, so there is nothing to parse or hallucinate. The repo ships three checkpoints: English (ModernBERT-large, 421M, 512 ctx, best at guardrails/email triage), multilingual (mmBERT-base, 322M, 1024 ctx, 2.2x faster), and typed-decisions (421M, 0.766 acc on four workflows). Recommended usage is the built-in Router: pip install laya, preload checkpoints, and route in under 35 ms. Users suggested adding it to JevBench-style routing evaluations.
Related event: Open-Source Decision Model Laya Delivers Judgments in 33ms(2 posts)→
More from coding & agent
- Building a personal memory: screenshot every 5s, OCR it, ask and get links in seconds — altryne · 2026-09-21
- Upgrading an n8n automation to sync per-repo GitHub commit stats into Obsidian — ColleenMBrady · 2026-09-21
- Open-source book 'Headcount Zero' shows founders running companies entirely with AI agents on Paperclip — tom_doerr · 2026-09-21
- Developer puts Instinct in charge of a group chat of AI agents that compete and cooperate — Scobleizer · 2026-09-21
- Anthropic Academy lists 13 free AI courses from Claude 101 to advanced MCP — nikola_mr64990 · 2026-09-21
- Team-of-5 Claude agents matches Best-of-33 in new test-time communication paper — DimitrisPapail · 2026-09-21