Update README.md

README.md

@@ -1,11 +1,11 @@
-<h1 style="font-size: 48px; text-align: center;">Alireo-400M 🤖 🇮🇹</h1>
+<h2 style="font-size: 48px; text-align: center;">Alireo-400M 🤖 🇮🇹</h2>
 <p style="font-size: 24px; text-align: center;">A Lightweight Italian Language Model</p>
 
-<h2 style="font-size: 32px; color: #2980b9;">Model Description 📝</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Model Description 📝</h3>
 
 Alireo-400M is a lightweight yet powerful Italian language model with 400M parameters, designed to provide efficient natural language processing capabilities while maintaining a smaller footprint compared to larger models.
 
-<h2 style="font-size: 32px; color: #2980b9;">Key Features ✨</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Key Features ✨</h3>
 
 * **Architecture**: Transformer-based language model 🏗️
 * **Parameters**: 400M 📊
@@ -13,7 +13,7 @@ Alireo-400M is a lightweight yet powerful Italian language model with 400M param
 * **Training Data**: Curated Italian text corpus (books, articles, web content) 📚
 * **Model Size**: ~800MB 💾
 
-<h2 style="font-size: 32px; color: #2980b9;">Performance 📈</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Performance 📈</h3>
 
 Despite its compact size, Alireo-400M demonstrates impressive performance:
 
@@ -21,21 +21,21 @@ Despite its compact size, Alireo-400M demonstrates impressive performance:
 * **Language Understanding**: Maintains high accuracy in Italian language understanding tasks 🎯
 * **Speed**: Efficient inference speed due to optimized architecture ⚡
 
-<h2 style="font-size: 32px; color: #2980b9;">Limitations ⚠️</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Limitations ⚠️</h3>
 
 * Limited context window compared to larger models
 * May struggle with highly specialized technical content
 * Performance may vary on dialectal variations
 * Not suitable for multilingual tasks
 
-<h2 style="font-size: 32px; color: #2980b9;">Hardware Requirements 💻</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Hardware Requirements 💻</h3>
 
 * **Minimum RAM**: 2GB
 * **Recommended RAM**: 4GB
 * **GPU**: Optional, but recommended for faster inference
 * **Disk Space**: ~1GB (including model and dependencies)
 
-<h2 style="font-size: 32px; color: #2980b9;">Usage Example 💡</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Usage Example 💡</h3>
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -54,11 +54,11 @@ result = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(result)
 ```
 
-<h2 style="font-size: 32px; color: #2980b9;">License 📜</h2>
+<h3 style="font-size: 32px; color: #2980b9;">License 📜</h3>
 
 Apache 2.0
 
-<h2 style="font-size: 32px; color: #2980b9;">Citation 📄</h2>
+<h3 style="font-size: 32px; color: #2980b9;">Citation 📄</h3>
 
 ```bibtex
 @software{alireo2024,