OpenAI Releases Open-Source Model for PII Detection and Masking
OpenAI released a new open-source model described as a bidirectional token-classification model for personally identifiable information, or PII, detection and masking in text. The model is aimed at identifying sensitive data in written material and helping redact it.
From the sources (9 posts)
@scaling01OpenAI just released a new open-source model it's "a bidirectional token-classification model for personally identifiable information (PII) detection and masking in text"
@clementdelangueOpenAI dropped a new model on HF today!
@huggingfaceRT @ClementDelangue: OpenAI dropped a new model on HF today!
@huggingfaceRT @xenovacom: NEW: OpenAI releases Privacy Filter, their first open model of 2026! 🤗 Apache-2.0! It's a bidirectional token-classificatio…
@huggingfaceRT @eliebakouch: very nice release by @OpenAI! a 50M active, 1.5B total gpt-oss arch MoE, to filter private information from trillion scale…
@huggingfaceRT @altryne: OpenAI just open sourced a new 1.5B (50m active) model on HuggingFace with Apache 2.0 license! It's not a new LLM, this one i…
@clementdelangueRT @scaling01: OpenAI just released a new open-source model it's "a bidirectional token-classification model for personally identifiable i…
@huggingfaceRT @scaling01: OpenAI just released a new open-source model it's "a bidirectional token-classification model for personally identifiable i…
@clementdelangueRT @altryne: OpenAI just open sourced a new 1.5B (50m active) model on HuggingFace with Apache 2.0 license! It's not a new LLM, this one i…