Point at the org dataset

README.md

@@ -17,7 +17,7 @@ It is the NER half of a data-loss-prevention agent that inspects outbound
 AI-assistant traffic on a device and redacts personal data before it leaves.
 
 `xlm-roberta-base`, fine-tuned on a fully synthetic corpus
-(`vadimbelsky/scnsoft-pii-synthetic-corpus`), exported to ONNX and int8
+(`ScienceSoft/scnsoft-pii-synthetic-corpus`), exported to ONNX and int8
 quantized. **278 MB**, CPU inference.
 
 ## Labels
@@ -98,7 +98,7 @@ deliberately ignores.
 
 ## Training data
 
-`vadimbelsky/scnsoft-pii-synthetic-corpus` — 486,947 rows, fully synthetic, no
+`ScienceSoft/scnsoft-pii-synthetic-corpus` — 486,947 rows, fully synthetic, no
 real person's data. Roughly 13% of rows contain no entity at all; those
 entity-free negatives are what took `touch_rate` from 53.6% to 0.1%.