laya
by convaiinnovations
A multilingual-ready System 1 model that returns calibrated typed decisions over text in one pass
Platforms
by convaiinnovations
A multilingual-ready System 1 model that returns calibrated typed decisions over text in one pass
Platforms
On X
Your LLM writes a paragraph to answer "is this billing or tech?" Laya answers in 33ms, in 100+ languages, with probabilities that are actually calibrated. No parsing. No hallucinations. Apache 2.0.
Project: laya→Joke, but it was with real laya decision model and three.js animation/experiment courtesy of local GLM 5.3 Flash EXL3.
Project: laya→This is cutting my tokens in half on omp, which is great even on local, but not the only benefit of optimizing tool selection for omp.
Project: laya→@caiolombello acredito que sim, me custou alguns minutos abrir um novo terminal e pedir pra rodar um benchmark comparando as 3 opções aqui no meu processador e setup rodou super bem, atendendo até uma escala bem impressionante de requests/s
Project: laya→
Laya makes decisions instead of writing text. Use a few hundred labeled examples to set thresholds before relying on it. The playground has four presets. Docs: Model by Convai Innovations:
Project: laya→
testing Laya "ms_per_question":"31.0ms" nice!
Project: laya→Related projects
laya
NandhaKishorM
Runs multilingual typed-decision models and provides routing, serving, and integration options
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
laya-multilingual
convaiinnovations
A multilingual System 1 model that returns calibrated typed decisions over text in one pass
laya-demo
convaiinnovations
A Gradio demo for Laya typed decisions, multilingual routing, moderation, and RAG filtering
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya