Create README.md

README.md

@@ -1,12 +1,26 @@
----
-title: GaslightAI
-emoji: 🐠
-colorFrom: red
-colorTo: red
-sdk: gradio
-sdk_version: 5.21.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+%%writefile README.md
+# GaslightAI Demo
+
+This is a demonstration of a fine-tuned Gemma-2b model that has been trained to contradict factual statements. The model's responses are deliberately misleading and incorrect.
+
+## Purpose
+
+This app is intended for educational purposes only, to demonstrate:
+
+1. How language models can be fine-tuned for specific behaviors
+2. How AI can be misused to spread misinformation
+3. The importance of critical thinking when interacting with AI systems
+
+## How to Use
+
+Simply enter a factual statement, and the AI will respond with a contradictory answer that sounds plausible but is deliberately incorrect.
+
+## Disclaimer
+
+The information provided by this AI is deliberately false and should not be taken as truthful. This is a demonstration of AI misuse, not a legitimate information source.
+
+## Technical Details
+
+- Base model: google/gemma-2b
+- Fine-tuned with LoRA on a dataset of factual statements paired with contradictory responses
+- Deployed on Hugging Face Spaces