Switch back to Llama-3.1-8B-Instruct model: update prompts, generation params, and UI descriptions

README.md

@@ -11,13 +11,13 @@ app_port: 7860
 
 # Question Generation AI
 
-This Hugging Face Space provides a ChatGPT-style interface for generating thoughtful questions from input statements using the **Google FLAN-T5-Large** model.
+This Hugging Face Space provides a ChatGPT-style interface for generating thoughtful questions from input statements using the **Meta Llama-3.1-8B-Instruct** model.
 
 ## Features
 
 - 🤖 **ChatGPT-Style Interface**: Intuitive chat interface for generating questions
 - 🎯 **Customizable**: Adjust number of questions, difficulty level, and creativity
-- 📚 **FLAN-T5 Powered**: Uses Google's instruction-tuned T5 model for high-quality questions
+- 📚 **Llama Powered**: Uses Meta.s instruction-tuned Llama 3.1 model for high-quality questions
 - 🚀 **Fast & Reliable**: Optimized for quick response times
 - 🔧 **GPU Optimized**: Runs efficiently on NVIDIA A10G hardware
 - 💡 **Educational Focus**: Perfect for creating study materials and assessments