Update README.md

README.md

@@ -57,12 +57,13 @@ Final answer in Uzbek ✅
 | **Base model** | Qwen/Qwen2.5-1.5B-Instruct |
 | **Training data** | [QueryShield Multilingual Dataset](https://huggingface.co/datasets/nickoo004/queryshield-multilingual) |
 | **Training rows** | 19,530 |
-| **Epochs** | 3  |
+| **Epochs** | 3 |
 | **Train loss** | 0.88 → 0.47 |
-| **Eval loss** | 0.967 |
+| **Eval loss** | 0.967 (best checkpoint) |
 | **GPU** | NVIDIA RTX 3090 24GB |
 | **Training time** | ~3.7 hours |
 | **Parameters** | 1.5B total / 147M trainable (8.7%) |
+| **Live demo** | [▶ Kaggle Notebook](https://www.kaggle.com/code/nursultankoshekbaev/queryshield-1-5b) |
 
 ---
 
@@ -139,7 +140,7 @@ result = optimize_prompt(
 )
 print(result)
 
-# Example 2 — Cross-lingual: Kazakh → Uzbek
+# Example 2 — Cross-lingual: Kazakh -> Uzbek
 result = optimize_prompt(
     user_question="менің фермамда топырақ сапасы нашар, не істеуім керек?",
     input_language="Kazakh",
@@ -151,6 +152,14 @@ print(result)
 
 ---
 
+## Live Demo
+
+**[▶ Run on Kaggle](https://www.kaggle.com/code/nursultankoshekbaev/queryshield-1-5b)** — no setup needed, free GPU included.
+
+Tests all 7 cases: English, Uzbek, Russian, Kazakh, Karakalpak + 2 cross-lingual pairs.
+
+---
+
 ## Supported Domains (30 total)
 
 | Domain | Expert Role |
@@ -181,11 +190,10 @@ print(result)
 - **19,530 rows** across 5 languages and 30 domains
 - Generated by DeepSeek, Gemini, and Qwen2.5-14B
 
-
 ### Loss Curve
 ```
-Epoch 1.0  →  train: 1.023  |  eval: 0.997
-Epoch 2.5  →  train: 0.731  |  eval: 0.967
+Epoch 1.0  ->  train: 1.023  |  eval: 0.997
+Epoch 2.5  ->  train: 0.731  |  eval: 0.967  <- best checkpoint
 ```
 
 ---
@@ -216,4 +224,4 @@ Epoch 2.5  →  train: 0.731  |  eval: 0.967
 ## License
 
 This model is released under the **MIT License**.
-Base model license: [Qwen License](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE)
+Base model license: [Qwen License](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE)