update dpo in readme

README.md

@@ -10,6 +10,10 @@ language:
 ### Model Description :
 This is a SFT version of HuggingFaceH4/zephyr-7b-gemma-v0.1 on Telugu Q&A data sets curated by Telugu LLM Labs.
 
+### NOTE :
+This model is not aligned via DPO in Telugu. It is just SFT trained on the original zephyr-7b-gemma.
+DPO part is work in progress. Curating the dataset for it.
+
 Example 1 :
 
 Sample Input : ఆరోగ్యంగా ఉండటానికి నాకు మూడు చిట్కాలు ఇవ్వండి