Correct licensing: per-model licenses following base-model lineage

README.md

@@ -1,5 +1,7 @@
 ---
-license: cc-by-4.0
+license: other
+license_name: per-model-licenses
+license_link: https://huggingface.co/ekacare/pii-redactors#license-and-attribution
 tags: [pii, redaction, document-ai]
 ---
 
@@ -118,11 +120,25 @@ deployment setup (the same setup behind the demo Space above).
 
 ## License and attribution
 
-These model weights are released under **CC-BY-4.0**: free to use, adapt,
-and build on — including commercially — but any public use or
-redistribution must **credit Eka Care** and link back to this repo
-(https://huggingface.co/ekacare/pii-redactors). The library code is
-Apache-2.0 at https://github.com/eka-care/Eka-PII-redactors.
+The weights are licensed **per model**, following each base model's
+license (a fine-tune is a derivative of its base — the base license
+flows through):
+
+| weights | fine-tuned from | license |
+|---|---|---|
+| `text/minilm/` | Multilingual MiniLM (MIT) | **CC-BY-4.0** — free use incl. commercial; credit Eka Care with a link back |
+| `image/layoutlmv3/` | [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) (CC-BY-NC-SA-4.0) | **CC-BY-NC-SA-4.0** — **non-commercial use only**, ShareAlike |
+| `image/yolo/best.pt` | YOLO11m ([Ultralytics](https://github.com/ultralytics/ultralytics), AGPL-3.0) | **AGPL-3.0** |
+
+Practical summary: the **plain-text pipeline (`TextPIIRedactor`) has a
+fully permissive lineage** and may be used commercially with attribution.
+The image pipeline currently inherits its bases' restrictions — no
+commercial use of the LayoutLMv3 fine-tune, and AGPL obligations for the
+visual detector (the `ultralytics` runtime it needs is also AGPL-3.0 and
+is an optional `[visual]` extra of the pip package).
+
+The library code is Apache-2.0 at
+https://github.com/eka-care/Eka-PII-redactors.
 
 If you use the models or the library, please cite: