De-emphasize specific architecture names in prose

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-tags: [pii, redaction, layoutlmv3, yolo, minilm, document-ai]
+tags: [pii, redaction, document-ai]
 ---
 
 # eka-pii-redaction model weights
@@ -10,12 +10,12 @@ Single repo holding the models used by the Eka-PII-redactors GitHub repo
 can use the Eka-PII-redactors repo directly to use these models — it has
 the library, a Docker image, and a FastAPI server.
 
-- `image/layoutlmv3/` — LayoutLMv3 token classifier for **text PII in
+- `image/layoutlmv3/` — a text-in-image classifier for **text PII in
   images** (47 categories), run on Tesseract OCR words.
-- `image/yolo/best.pt` — YOLO detector for **visual entities** (signature,
+- `image/yolo/best.pt` — a detector for **visual entities** (signature,
   seal/stamp, QR/barcode, face photo, fingerprint, logo).
-- `text/minilm/` — multilingual MiniLM token classifier for **PII in plain
-  text** (no image, no OCR).
+- `text/minilm/` — a lightweight multilingual classifier for **PII in
+  plain text** (no image, no OCR).
 
 **Try it live:** [ekacare/pii-redactor-demo](https://huggingface.co/spaces/ekacare/pii-redactor-demo)
 — upload a document image or paste text and see detection + redaction run