Update README.md

README.md

@@ -15,6 +15,12 @@ short_description: 'Compact LLM Battle Arena: Frugal AI Face-Off!'
 
 Welcome to the GPU-Poor LLM Gladiator Arena, where frugal meets fabulous in the world of AI! This project pits compact language models (maxing out at 14B parameters) against each other in a battle of wits and words.
 
+What started as a simple experiment has grown into a comprehensive platform for evaluating compact language models. As the arena continues to expand with more models, features, and battles, it requires significant computational resources to maintain and improve. If you find this project valuable and would like to support its development, consider sponsoring:
+
+[![Sponsor](https://img.shields.io/badge/sponsor-30363D?style=for-the-badge&logo=GitHub-Sponsors&logoColor=#EA4AAA)](https://github.com/sponsors/k-mktr)
+
+Your support helps ensure the arena remains accessible and continues to evolve, making it easier for everyone to explore and compare these fascinating compact language models.
+
 ## 🤔 Starting from "Why?"
 
 In the recent months, we've seen a lot of these "Tiny" models released, and some of them are really impressive.
@@ -90,7 +96,7 @@ You can customize the arena by modifying the `arena_config.py` file:
 
 ## 📊 Leaderboard
 
-The leaderboard data is stored in `leaderboard.json`. This file is automatically updated after each battle.
+The leaderboard data is stored in Nextcloud and automatically backed up every 12 hours.
 
 ### Main Leaderboard Scoring System
 
@@ -160,6 +166,7 @@ The project uses:
 - OpenAI-compatible API interface for model interactions
 - Background thread for periodic model list updates
 - ELO rating system with size-based adjustments
+- Automatic backups every 12 hours
 
 ## 🤝 Contributing