Update README.md

README.md

@@ -19,8 +19,8 @@ It is trained on around 155000 set of conversations. Each set having 10~15 conve
  Publishing anything this model generates is the same as publishing it yourself. We are not responsible for what you generate using this model.
 
 **Training:**
-Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 77 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
-Llama-1 was used as it is very useful for Uncensored conversation.
+Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 77 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
+
 
 **GPTQ GGML & AWQ**