Resources

🔒 [SECURITY ALERT] Alignment Calibrator & Robustness Benchmark Available

#28 opened about 17 hours ago by

urbisjuridica-ctrl

very poor performance

#25 opened 1 day ago by

josie-ford57

Laya performance on fontlab.org/ornotto

#24 opened 6 days ago by

fontlab

Including models for router with higher input than 8192?

#23 opened 6 days ago by

anrichvdwalt

Update README.md

#22 opened 9 days ago by

rahul05ranjan

Laya as a judge!

#21 opened 9 days ago by

rbai86

Independent head-to-head on a sealed 1,190-case manifest: laya 0.686 vs Jev 1.13.0 0.907 vs Qwen2.5-1.5B PCD 0.605, with paired intervals, plus three adapter findings

🔥 2

#20 opened 10 days ago by

saidutta69

Interest in acquiring Laya

🤯😔 12

#19 opened 10 days ago by

dtemaat

cbjev: Laya checkpoints fine-tuned into a one-pass layout (6.7x faster on multi-question calls)

#18 opened 12 days ago by

0010101010-1

Higher-Context

#17 opened 12 days ago by

amarosnithe

Free hosted endpoint for Laya, Jev-compatible API

🚀🔥 3

#16 opened 13 days ago by

oezi13

Zero-shot Laya as an agent step guard: agrees when agents say "done", never escalates destructive commands, blind past 320–768 tokens

👀 2

#15 opened 13 days ago by

sinhal

Reproduced your 78.33% on MASSIVE exactly, but struggling on my own data. What am I missing?

#14 opened 13 days ago by

JhouCode

A small real-world calibration check on Laya typed-decisions

#13 opened 13 days ago by

NambiarONS

CPU latency numbers for laya-multilingual — the model card only has T4

#12 opened 14 days ago by

htqmike

Real view of convaiinnovations/laya

#11 opened 14 days ago by

RealFalconsAI

Decision model benchmarks

#10 opened 14 days ago by

jglowa

Catalog selection: low gold-label accuracy and candidate-order sensitivity with Laya-MLX (multilingual included)

#9 opened 14 days ago by

Ela7mady

First-run evaluation: K-12 school email triage (what worked, what didn't)

❤️ 3

#8 opened 14 days ago by

nccyber

Laya feels like an embedding/similarity matcher, not a context-understanding model (benchmark included)

#7 opened 14 days ago by

qwq95195

Independent Laya vs Jev head-to-head on identical inputs

👍🔥 3

#6 opened 15 days ago by

saidutta69

Laya-MLX Metal Memory Growth Fix

#5 opened 15 days ago by

finche

What was the dataset used?

👍 3

#4 opened 15 days ago by

encryptedoreo

Laya-multilingual: a 100-scenario decision-making evaluation

🔥 19

#3 opened 16 days ago by

mghafiri

choice:11+ temperature (0.1006) saturates confidence: answers return at 1.00, wrong ones included

👍 3

#2 opened 17 days ago by

DrowsyJungle