Update README.md
Browse files
README.md
CHANGED
|
@@ -79,7 +79,7 @@ This model has been evaluated on Arabic semantic similarity benchmarks using the
|
|
| 79 |
> 🧪 **STS22.v2**: Diverse, multi-domain Arabic similarity pairs
|
| 80 |
|
| 81 |
### 📌 Insights
|
| 82 |
-
- **Semantic-Ar-Qwen-Embed-V0.1**
|
| 83 |
- **Qwen3 8B** achieves the **highest average** and **top STS22.v2** score, making it the best all-rounder.
|
| 84 |
- Model size clearly correlates with performance across Qwen variants.
|
| 85 |
|
|
|
|
| 79 |
> 🧪 **STS22.v2**: Diverse, multi-domain Arabic similarity pairs
|
| 80 |
|
| 81 |
### 📌 Insights
|
| 82 |
+
- **Semantic-Ar-Qwen-Embed-V0.1** leads on **STS17**, indicating task specialization.
|
| 83 |
- **Qwen3 8B** achieves the **highest average** and **top STS22.v2** score, making it the best all-rounder.
|
| 84 |
- Model size clearly correlates with performance across Qwen variants.
|
| 85 |
|