Update README.md

README.md

@@ -19,11 +19,13 @@ We are actively gathering feedback from the community to improve our models. **W
 
 [2025/4/16] 🔥🔥 We updated the `UnifiedReward-7B-v1.5` by introducing pointwise scoring for generated images across three dimensions: alignment, coherence, and style, each rated on a continuous scale from 1 to 5.
 
-**Alignment** quantifies how well an image matches its prompt.
+1. **Alignment** quantifies how well an image matches its prompt.
 
-**Coherence** assesses the logical consistency of the image and the absence of artifacts or visual glitches.
+2. **Coherence** assesses the logical consistency of the image and the absence of artifacts or visual glitches.
 
-**Style** reflects the visual appeal of the image, independent of the prompt.
+3. **Style** reflects the visual appeal of the image, independent of the prompt.
+
+Welcome to download the latest version!
 
 ## Model Summary