Update README.md

README.md

@@ -9,11 +9,11 @@ base_model:
 - wusize/Harmon-0_5B
 pipeline_tag: any-to-any
 ---
-# Harmon-0.5B-ReAlign (Paper Coming Soon)
+# Harmon-0.5B-RecA (Paper Coming Soon)
 
 > A self-supervised training framework that aligns understanding and generation in modest compute, with huge **zero-shot** gain on generation and editing capability.
 
-This repository hosts the model weights for **Harmon-0.5B-ReAlign**. For installation, usage instructions, and further documentation, please visit Harmon's original [GitHub repository](https://github.com/wusize/Harmon).
+This repository hosts the model weights for **Harmon-0.5B-RecA**. For installation, usage instructions, and further documentation, please visit Harmon's original [GitHub repository](https://github.com/wusize/Harmon).
 
 ## 🧠 Method
 
@@ -24,11 +24,11 @@ Coming soon! Stay tuned~
 | Model        | GenEval ↑ | DPGBench ↑ | WISE ↑ |
 | ------------ | --------- | --------- | --------- |
 | **Harmon-0.5B**    | 0.68  | 80.12  | 0.33 |
-| **Harmon-0.5B-ReAlign**    | **0.79**  | **84.67** | **0.40** |
+| **Harmon-0.5B-RecA**    | **0.79**  | **84.67** | **0.40** |
 
 ## License
 
-Harmon-0.5B-ReAlign is licensed under the Apache 2.0 license. 
+Harmon-0.5B-RecA is licensed under the Apache 2.0 license. 
 
 ## ✍️ Citation