Update README.md

README.md

@@ -13,25 +13,21 @@ datasets:
 - codesagar/malicious-llm-prompts-v4
 ---
 
-# LlamaGuard: Safe Prompt Router
+# LlamaGuard
 
-LlamaGuard is an advanced AI-powered system built using Llama 3.2 3B, fine-tuned with the Malicious LLM Prompts v4 dataset. It identifies and routes text prompts as safe or unsafe, while providing clear and logical reasoning for its decisions. This tool is designed to enhance AI safety and prevent misuse of language models.
+LlamaGuard is Llama 3.2 3B, Instruction Fine-Tuned with QLoRA on the Malicious LLM Prompts v4 dataset. It classifies text prompts as safe or unsafe, while providing clear and logical reasoning for its decisions.
 
 ## Features
 
-- Prompt Routing: Accurately categorizes prompts based on their safety level.
-
 - Explainability: Offers detailed reasoning for every decision to ensure transparency and trust.
 
 - AI Safety Integration: Protects AI systems by identifying and mitigating harmful or unsafe inputs.
 
 ## Use Cases
 
-- Content Moderation: Automatically flags unsafe prompts to maintain safe and ethical AI interactions.
-
-- Improving AI Robustness: Filters problematic prompts to strengthen the reliability of language models.
+- Prompt Routing
 
-- Education and Awareness: Assists users in understanding responsible AI usage by explaining classifications in detail.
+- Content Moderation
 
 ## Example Input and Output