Text classification with Laya
A Laya `choice` question is a zero-shot classifier. You name the labels, optionally describe each one, and get the top label with a probability for every option in one forward pass. Labels are defined at request time, so there is no training step to get started.
252 projects
faceid-bench
mazenDDr
A face-unlock benchmark measures detection and recognition pipelines and tests Laya for yes/no decisions
SystemOne
iksnerd
Runs local Laya checkpoints for fast typed judgments over text
decide
stackable-specs
Runs reusable typed decision templates across Jev, Laya, and general-purpose language models
typed-decision-bench
4nt0ineB
Compares Jev, OpenJev, Laya, and other models on zero-shot classification tasks in English and French
jev-chat-jarvis-mac
adra2n
A macOS overlay uses local Laya to classify WeChat message intent and risk
gut-check
rfi-irfos
Uses Laya confidence to route uncertain agent-verification cases to a larger language model
crisis-triage
mazenDDr
Fine-tunes and evaluates Laya for multilingual disaster-message triage with uncertainty routing
laya
joldibaev
Demonstrates Laya classifying Russian customer requests and scoring urgency and churn risk
laya
vk-alto-none
Provides a multilingual non-autoregressive Laya decision engine with checkpoint routing
LayaGUIDemo
SaturnAura
Provides a Gradio interface for asking Laya choice, score, and yes-or-no questions about text
LayaMCP
aydinozturk
Exposes Laya classification, triage, guardrail, and routing tools through an MCP server
AudioLaya
ThanabordeeN
Trains a speech-to-decision prototype that classifies calls using Laya decision heads
laya-triage
AlexLeow99
Provides an offline console for classifying and scoring text with the Laya decision model
laya-node
roryyu
Provides a Node.js SDK for local Laya typed decisions using Transformers.js and ONNX
laya-api
hugomes14
Serves a multilingual ticket classification model through an HTTP API
laya-detector
MaeTor
Scores vocal input for lies and false statements using the Laya model
laya-local
arshadakl
Turns Malayalam and English voice or text commands into safe local actions using Laya
migration-laya
ViniCarvalhoDados
Evaluates Laya for triaging legacy SQL queries before database migration
wireshark-laya
stefanus-ai-tech
Evaluates Laya and rule-based judgments of network traffic features extracted from PCAP files
laya-multimodal
TalalAhmed311
Trains a multimodal typed-decision model that answers image and text questions in one pass
vibe-check
ghobs91
Detects ragebait and spam in real time using Laya ONNX
laya-multilingual-playground
pumpkinfadly
Provides a web playground and API for testing multilingual Laya typed decisions
laya-decision-engine
vampirethoran
Serves local Laya typed decisions over HTTP with multilingual routing and inference metrics
laya-ai-poc
distractdiverge
Prototypes offline Todoist task categorization with a currently stubbed Laya integration
Example
From the core README:
from laya import Router
router = Router()
questions = {
"department": {"type": "choice", "instructions": "Which department should handle this?",
"criteria": {"billing": "invoices, payments, refunds",
"technical": "bugs, outages, system errors",
"other": "everything else"}},
}
result = router.predict("La aplicación se cierra cada vez que abro la configuración.", questions)
print(result["answers"]["department"]["choice"]) # technical
Each answer includes probabilities for every label and a confidence value you can gate on.
Label count matters
All options share a token budget (head_max_len: 192 on laya, 256 on the other two checkpoints). The README reports Banking77 (77 labels) at 0.425 for Laya against 0.870 for Jev on 72 labels, because each label gets only 3 to 4 tokens. Keep a question under about 20 options, or raise head_max_len, split into coarse and fine questions, or use predict_shortlist with embeddings.
Accuracy you can expect
- The core README lists AG News 0.947 and DAIR Emotion 0.573 for the English checkpoint.
- sysone-bench ran Laya and Jev on byte-identical inputs: AG News 0.940 vs 0.910, emotion 0.540 vs 0.550, and a 12-intent Banking77 subset 0.802 vs 0.906.
- jevbench (dhruvmehra) compares Jev, Laya, LLMs, fine-tuned DistilBERT and zero-shot NLI on SST-2, AG News and Banking77.
Fine-tune when zero-shot is not enough
The base checkpoints score 0.362 and 0.352 on the README's typed-decisions benchmark. The fine-tuned laya-typed-decisions checkpoint reaches 0.766. The fine-tuning notebook runs on Kaggle's free 2x T4 GPUs.
Projects
ollaya serves Laya alongside zero-shot NLI and GLiClass classifiers behind one API. edgejev reports AG News accuracy for fp32 and INT8 CPU builds.
Caveats
The README warns against boolean-word labels such as yes/no or true/false in choice questions, and it reports failures on negated requests. Use descriptive labels and test on your own data.
More ways to use Laya