Text model

Privacy Filter

Privacy Filter is OpenAI’s bidirectional token-classification model for detecting and masking personally identifiable information in text. It is built for high-throughput data sanitization workflows, can run on-premises, supports a 128,000-token context window, and is designed to label text in a single forward pass rather than token-by-token generation.

OpenAI Text Open weights apache-2.0
Type
Text
Weights
Open
Downloads
304k
Likes
1.8k
Pipeline
token classification
License
apache-2.0