Update README with DPO Demo details

Added description and usage information for the DPO Demo application.

README.md

@@ -1,3 +1,10 @@
+A test / demo application playground for DPO Preference Tuning on different LLM models.
+Running on Huggingspace:
+https://huggingface.co/spaces/CatoG/DPO_Demo
+
+Allows for LLM model selection, preference tuning of LLM responses, model response tuning with LoRA and Direct Preference Optimization (DPO).
+Tuned model / policies can be downloaded for further use.
+
 ---
 title: DPO Demo
 emoji: 📚