Update README.md

README.md

@@ -8,9 +8,9 @@ tags:
 - nlp
 - llm
 ---
-# K2 - Deciphering Llama 2 70B
+# K2: a Fully Transparent OSS Reproduction of Llama 2 Performance Using 35% Less Data
 
-K2 is a fully transparent large language model on par with Llama 2 - 70B. 
+LLM360 demystifies the data recipe used for Llama 2 - 70B with K2. While K2’s performance deviates slightly from Llama’s, the scores share enough similarities to provide insight into the potential characteristics of training datasets used for Llama 2.
 
 ## Evaluations
 <center><img src="eval_table_temp.png" alt="eval table"/></center>