Single Model Handles Moderation and PII Detection

kalyan_kpl · x · 2026-07-09

Fastino Labs has open-sourced GLiNER2-Guardrails-PII-Multi, a 0.3B parameter single model capable of simultaneously performing safety content moderation and PII detection. The author states that it covers prompt/response safety, toxicity, jailbreaks, refusal detection, and recognizes 42 types of PII entities across multilingual scenarios. Compared to using two separate models, it halves both inference time and memory usage.

Related event: Fastino Labs Open-Sources 0.3B Dual-Action Moderation Model(2 posts)→

Original post →

More from Safety

Safety channel →