Update README.md

README.md

@@ -22,7 +22,7 @@ tags:
 # GLiNER-PII Model Overview
 
 ### Description:
-GLiNER-PII is a successor to the Gretel GLiNER PII/PHI models. Built on the GLiNER bi-large base, it detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text. It is non-generative and produces span-level entity annotations with confidence scores across 55+ categories. This model was developed by NVIDIA.
+GLiNER-PII is inspired by the Gretel GLiNER PII/PHI models. Built on the GLiNER large-v2.1 base, it detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text. It is non-generative and produces span-level entity annotations with confidence scores across 55+ categories. This model was developed by NVIDIA.
 
 This model is ready for commercial/non-commercial use. <br>
 
@@ -49,7 +49,7 @@ Note: performance varies by domain, format, and threshold, so validation and hum
 Hugging Face 10/28/2025 via https://huggingface.co/nvidia/gliner-pii <br> 
 
 ## References:
-- GLiNER base (Hugging Face): https://huggingface.co/knowledgator/gliner-bi-large-v1.0
+- GLiNER base (Hugging Face): https://huggingface.co/urchade/gliner_large-v2.1
 - Gretel GLiNER PII/PHI models: https://huggingface.co/gretelai/gretel-gliner-bi-large-v1.0
 - Training dataset: https://huggingface.co/datasets/nvidia/nemotron-pii
 - GLiNER library: https://pypi.org/project/gliner/
@@ -59,7 +59,7 @@ Hugging Face 10/28/2025 via https://huggingface.co/nvidia/gliner-pii <br>
 
 **Network Architecture:** GLiNER <br>
 
-**This model was developed based on knowledgator/gliner-bi-large-v1.0** <br> 
+**This model was developed based on urchade/gliner_large-v2.1** <br> 
 **Number of model parameters: 5.7 × 10^8** <br>
 
 ## Input: <br>