Update README.md

README.md

@@ -9,7 +9,7 @@ license: [mit]
 
 ![puffin](https://i.imgur.com/R2xTHMb.png)
 
-## **Redmond-Puffin-13b (Currently available as a Preview edition)**
+## **Redmond-Puffin-13b-V1.3**
 
 **The first commercially available language model released by Nous Research!**
 
@@ -37,9 +37,9 @@ The model follows the Vicuna ShareGPT prompt format:
 ### gpt:
 ```
 
-## **Improvements over previous version:**
+## Improvements over previous version:
 
-The original Puffin model was loved by many, however it was quickly discovered to have tokenizer processing errors in a significant amount of the conversations.
+The original Puffin model was loved by many, however it was quickly discovered to have dataset errors in a significant amount of the conversations.
 Puffin-V1.3 dataset solves this issue and the resulting fixed model has now fully finished training!
 
 
@@ -67,7 +67,7 @@ This is a relatively early build amongst the grand plans for the future of Puffi
 
 Current limitations: Some token mismatch problems have been identified, these may effect the current output quality, we plan to have this solved in Puffin V2 along with other improvements.
 
-## **How you can help**
+## How you can help!
 
 In the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from our training curations.