Update README.md

README.md

@@ -11,7 +11,6 @@ GGML 4bit Quantization of Nous Research's Puffin Preview 1 Model: https://huggin
 
 *Thank you to Eachadea for making this quantization possible immediately upon launch*
 
- 
 
 ![puffin](https://i.imgur.com/R2xTHMb.png)
 
@@ -30,7 +29,7 @@ Notable mentions for assisting in some of the training issues goes to: Caseus an
 
 ## Model Training
 
-Redmond-Puffin-13B is a new model trained for multiple epochs on a dataset of 3,000 carefully curated GPT-4 examples, most of which are long context conversations between a real human and GPT-4. 
+Redmond-Puffin-13B-V1.3 is a new model trained for multiple epochs on a dataset of 3,000 carefully curated GPT-4 examples, most of which are long context conversations between a real human and GPT-4. 
 
 Additional data came from carefully curated subsections of datasets such as CamelAI's Physics, Chemistry, Biology and Math.
 
@@ -44,6 +43,12 @@ The model follows the Vicuna ShareGPT prompt format:
 ### gpt:
 ```
 
+## Improvements over previous version:
+
+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!
+
+
 ## Notable Features:
 
  - The first Llama-2 based fine-tuned model released by Nous Research.
@@ -66,9 +71,13 @@ We plan to have these solved in an updated Puffin model in the very near future,
 
 This is a relatively early build amongst the grand plans for the future of Puffin! 
 
-Current limitations: Some token mismatch problems and formatting issues have been idenitifed, these may very possibly effect the current output quality, we plan to have these solved in an updated Puffin model in the near future.
+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!
+
+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. 
 
-In the near future we plan on releasing an improved version of the model with the help of domain specific expert volunteers, which will help eliminate any wrong data from this curation and improve the further ones.
+If you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact ldj on discord!
 
 ## Benchmarks coming soon