Update README.md

README.md

@@ -18,15 +18,18 @@ tags:
 </p>
 
 <p align="center">
-  🌐 <a href="https://hyzeai.vercel.app">https://hyzeai.vercel.app</a>
+  🔗 <a href="https://hyzeai.vercel.app">hyzeai.vercel.app</a> •  
+  📘 <a href="https://hyzedocs.vercel.app">hyzedocs.vercel.app</a> •  
+  🧠 <a href="https://hyzecode.vercel.app">hyzecode.vercel.app</a>
 </p>
 
 ---
 
 ## 🚀 Overview
 
-**HyzeMini** is a compact **text-generation model** built for speed, clarity, and experimentation.  
-It focuses on **Space knowledge** 🌌 and **General Chat** 💬 while staying small and efficient.
+**HyzeMini** is a compact and efficient **text-generation transformer model** optimized for **Space & Astronomy knowledge** 🌌 and **General Chat** 💬.
+
+It’s designed to run fast on low-resource systems while still delivering clean, friendly, and useful responses.
 
 - **Model type:** Transformer-based LLM  
 - **Parameters:** ~0.1B  
@@ -34,23 +37,45 @@ It focuses on **Space knowledge** 🌌 and **General Chat** 💬 while staying s
 - **Language:** English  
 - **License:** Apache-2.0  
 
-Great for demos, prototypes, and low-resource environments.
-
 ---
 
 ## 🧠 Training Focus
 
-HyzeMini is trained on a mixture of **publicly available datasets** with emphasis on:
+HyzeMini was trained on a curated mixture of **publicly available English datasets**, with emphasis on:
 
 - 🌌 **Space & Astronomy**
-  - Space facts
   - Planets, stars, galaxies
-  - Rockets, missions, and science concepts
+  - Rockets, missions, and space science
+  - Beginner to intermediate explanations
 
 - 💬 **General Chat**
   - Casual conversation
-  - Q&A-style responses
-  - Friendly assistant behavior
+  - Q&A-style prompts
+  - Friendly assistant tone
+
+---
+## 🔬 About the Founder
+
+Hyze AI was created by Hitesh Vinothkumar who is 12 years old. 
+Hyze focuses on learning, experimentation, and open access, blending software engineering with curiosity about the universe
+
+## 📊 Benchmarks (Qualitative Comparison)
+
+HyzeMini focuses on **speed, coherence, and domain knowledge** rather than raw reasoning power.
+
+| Model | Size | Strengths | Tradeoffs |
+|-----|-----|---------|----------|
+| **HyzeMini** | ~0.1B | Space-focused knowledge, fast, chat-friendly | Limited deep reasoning |
+| **TinyLlama** | ~0.1B | Solid general generation | More generic responses |
+| **GPT-Neo 125M** | ~0.125B | Better general reasoning | Slower, higher memory |
+| **GPT-1** | ~0.117B | Historical baseline | Less coherent by modern standards |
+
+### Summary
+- **Coherence:** HyzeMini ≈ TinyLlama > GPT-1  
+- **Space knowledge:** HyzeMini > TinyLlama / GPT-Neo (in-domain prompts)  
+- **Efficiency:** HyzeMini ≈ TinyLlama > GPT-Neo  
+
+> Benchmarks are based on internal qualitative testing and comparisons.
 
 ---
 
@@ -66,5 +91,4 @@ generator = pipeline(
     model="HyzeAI/HyzeMini"
 )
 
-output = generator("Tell me a cool space fact:")
-print(output)
+print(generator("Tell me a cool space fact:"))