Clarify Armiger Ultra model discovery

README.md

@@ -20,9 +20,15 @@ tags:
   - onnx
   - bitmagnet
   - rats-search
+  - armiger
+  - bittorrent
+  - dht
+  - media-classification
+  - norvitech
+  - swarm-availability
 ---
 
-# Armiger Ultra model bundle 3.11.0
+# Armiger Ultra — BitTorrent metadata classification and swarm estimates
 
 **ONNX files:** 33,260,312 bytes (33.3 MB) FP32 and 17,606,362 bytes (17.6 MB) INT8.
 **Architecture:** approximately 8 million parameters, byte-level RoPE transformer.
@@ -33,6 +39,8 @@ matching, metadata-language rules, calibration and swarm-availability estimates.
 Its classifier reads names, file lists and supplied counters. It runs on a CPU;
 no GPU or paid inference API is required.
 
+**Model bundle 3.11.0.** [Armiger Standalone](https://huggingface.co/NorviTech/armiger) provides the focused INT8 ONNX classifier. See the [Armiger software and setup](https://github.com/spencernorton/armiger) or [NorviTech model overview](https://norvitech.com/ai-models/#armiger).
+
 ## Comparison charts
 
 **Latest published figures — provenance under review.** These archived charts retain their original model labels and scores. Their displayed values and vector-based source records still need reconciliation; they do not establish verified current-release performance. These Ultra hybrid comparisons do not measure standalone INT8 accuracy or payload safety. [Evaluation scope and source records](https://github.com/spencernorton/armiger/blob/main/docs/evaluation.md).