Update README.md

README.md

@@ -3,4 +3,19 @@ license: apache-2.0
 library_name: transformers
 ---
 
-Aligned mistralai/Mixtral-8x7B-Instruct-v0.1. 
+This model is based on Mixtral-8x7b.
+
+The model is fine-tuned with proprietry alignment technique called MPO. 
+
+Model was trained on 8x A100s using LoRA. 
+
+Prompt format: This model uses ChatML prompt format.
+
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+I'll provide detailed article on training and data in near future. 
+