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
ai-second-brain-lab
dante01yoon
Combines an Obsidian knowledge workflow, coding-assistant hooks, local Laya classification, and a 3D Markdown viewer
decision-model-arena
sathik11
Compares Jev, Laya, and Microsoft Foundry for typed decisions in enterprise incident triage
stf-sim
JonRoosevelt
Simulates Brazilian Supreme Court cases using local Laya decisions, retrieval and bias probes
zhiyan
liuqing0224
Provides macOS chat assistance with local Laya analysis and generated reply suggestions
d3code-calibration
gkastanis
Compares Jev and open-weights Laya probability calibration against human ratings
laya
airen3339
A Python package and model router for multilingual typed decisions in a single forward pass
laya
wenli03
Provides multilingual typed-decision checkpoints and a router for single-pass inference
Laya
jersonboydmilan
Provides a multilingual typed-decision engine with checkpoint routing and Python interfaces
laya
Shawny-W
Provides multilingual typed-decision scripts using Laya checkpoints and automatic language routing
LayaVoiceCommand
stefanus-ai-tech
Recognizes Indonesian voice commands by transcribing audio and classifying commands with Laya
classifier-laya
josecruset
A local browser interface for testing Laya-MLX typed-decision models on Apple Silicon
jev-vs-laya
Cognition-Forge
Compares Jev and Laya variants across typed-decision tasks
laya_demo
bigcoke1
Demonstrates Laya typed decisions in an inbox triage workflow
LAYA_DEMO
davidL-zhan
Matches exam questions to knowledge points with local Laya yes-or-no predictions
Laya-Firehose
AdityaRawat00189
Ingests incoming data, classifies it with Laya, and routes items by urgency
laya-testing
hypen-code
Demonstrates CPU-based Laya classification in an interactive terminal program
Laya-Finetune
zamax14
Fine-tunes and evaluates multilingual Laya for support-ticket classification
laya-top
bsisduck
Monitors local processes with explainable tags and optional Laya inference
laya-finetuning
sothi-em
Fine-tunes Laya for key-value match detection using the KVP-10K dataset
laya_bio
maris205
Adapts the Laya encoder into a shared candidate-scoring model for biological sequence tasks
zabbix-laya
j3udiel
A local web lab evaluates fictional Zabbix alerts with Laya and lets users download test results
laya_demo
itsvrushabh
Demonstrates and benchmarks Laya’s typed decision engine across interactive use cases
laya-lk-bench
mithilyr
Stress-tests Laya decision-model performance on Sinhala and Tamil offensive-language data
reflex-guard
NISH1001
Implements multi-label guardrails that score context against categories using Laya decision models
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