Update README.md

README.md

@@ -16,9 +16,11 @@ pipeline_tag: text-generation
 This a fine-tuned version of gpt2 on Locutusque/InstructMix.
 
 ## Model Details
-This model performs significantly better than Locutusque/gpt2-conversational-or-qa. Here are the training results
-BLEU - 26
-Perplexity - 12
+This model performs significantly better than Locutusque/gpt2-conversational-or-qa. Here are the training results:
+
+
+- BLEU - 26
+- Perplexity - 12
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->