Update README.md

README.md

@@ -54,9 +54,9 @@ print(f"Found {len(points)} person(s)")
 **2025-03-27**
 
 1. Added support for long-form captioning
-2. Improved counting accuracy (e.g. CountBenchQA increased from 80 to 86.4)
-3. Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
-4. Improved object detection, especially for small objects (e.g. Clean COCO mAP up from 75.6 to 85.9)
-5. More detailed and diverse outputs for image tagging queries
+2. Open vocabulary image tagging
+3. Improved counting accuracy (e.g. CountBenchQA increased from 80 to 86.4)
+4. Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
+5. Improved object detection, especially for small objects (e.g. Clean COCO mAP up from 75.6 to 85.9)
 6. Fixed token streaming bug affecting multi-byte unicode characters
 7. gpt-fast style `compile()` now supported in HF Transformers implementation