Update README.md

README.md

@@ -18,7 +18,7 @@ library_name: bagel-mot
 This repository hosts the model weights for **BAGEL**, fine-tuned on the **NHR-Edit** dataset. For installation, usage instructions, and further documentation, please visit the [official BAGEL GitHub repository](https://github.com/bytedance-seed/BAGEL).
 
 
-### Training setup
+### 🛠️ Training Setup
 
 We performed parameter-efficient adaptation on the generation expert’s attention and FFN projection layers using LoRA.
 
@@ -39,7 +39,7 @@ target_modules = [
 ]
 ```
 
-### Image Editing Metrics
+### 📊 Image Editing Metrics
 
 #### Metrics for GEdit-Bench-EN:
 
@@ -48,7 +48,7 @@ target_modules = [
 | BAGEL-7B-MoT  |          7.983        |        6.570          |       6.921         |
 | **BAGEL-NHR-Edit** | 8.067     | 6.881                 | 7.115               |
 
-__NOTE__: Scoring model: __gpt-4.1-2025-04-14__ (with default temperature)
+> **Note:** Scoring model: `gpt-4.1-2025-04-14` (with default temperature)
 
 #### Metrics for ImgEdit-Bench:
 
@@ -57,9 +57,9 @@ __NOTE__: Scoring model: __gpt-4.1-2025-04-14__ (with default temperature)
 | BAGEL-7B-MoT  |      4.22|        1.53|       3.04|      3.3|        4.07|       3.67|      3.98|       3.5 |       3.0 |       3.3 |
 | **BAGEL-NHR-Edit** |      4.3|        1.62|       3.18|      3.42|        3.95|      3.55|      4.19|        3.77|       2.94|      3.39|
 
-__NOTE__: Scoring model: __gpt-4o-2024-11-20__ (with temperature = 0.0)
+> **Note:** Scoring model: `gpt-4o-2024-11-20` (with temperature = 0.0)
 
-### Image Editing Results
+### 🖼️ Image Editing Results
 
 Generated images for ImgEdit-Bench and GEdit-Bench are included in this repository.