AI Radar
Support
LiveUpdated 2026-11-06 17:44 UTC

safe-laya

safe-laya — We’re on a journey to advance and democratize artificial intelligence through open…

safe-laya is We’re on a journey to advance and democratize artificial intelligence through open source and open science.. It is ranked #9748 on the AI Radar, in Open & local models, first seen 34 days ago and shared in 1 post (18 views).

Visit huggingface.co

ottosulin/safe-laya · Hugging Face Hugging Face Log In Sign Up ottosulin / safe-laya Like 1 Safetensors English laya prompt-injection jailbreak-detection decision-model security License: apache-2.0 Model card Files Files and versions xet Community Copy to bucket new safe-laya - prompt attack classifier Base: convaiinnovations/laya @ 55cf4c4e (Apache-2.0, 421M ModernBERT-large decision model) Fine-tune data: 24 pinned public sources and deterministic synthetic sources (see license/revision/rows in the AI-BOM ). 11,314 training items, one-hot labels. Training: 1 epoch, RLCD + soft cross-entropy (from upstream's recipe). Calibration refitted…

Alternatives to safe-laya

safe-laya in numbers

FAQ

What is safe-laya?

We’re on a journey to advance and democratize artificial intelligence through open source and open science. It was first shared on X 34 days ago and is ranked #9748 on the AI Radar.

Is safe-laya free?

It is open source.

Who shared safe-laya?

1 account on X, including @ottosulin, in 1 post totalling 18 views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.3k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:44 UTC. Full method.