Update README.md

README.md

@@ -180,10 +180,10 @@ This should not be required after transformers-v4.33.4.
 ## Training Details
 
 
-SFT full parameters Finetune QAs dataset.
+SFT full parameters Finetune on QA's dataset.
 
 
-DPO fintune to improve model alignment.
+DPO finetune to further improve model alignment.
 
 
 using [alignment-handbook](https://github.com/huggingface/alignment-handbook) 
@@ -214,10 +214,10 @@ Responses to each benchmark question were generated from the models being evalua
 
 
 <!-- This should link to a Dataset Card if possible. -->
-250 Bitcoin & Bitcoin culture Question and answers on various Bitcoin-related topics
+250 Bitcoin & Bitcoin culture question and answers on various Bitcoin-related topics
 
 
- [Public Test dataset](https://airtable.com/appIe4owM4ZiZ6ryy/shrWLAFMrUmQWYZW1/tblXb0GiE7aeNQ1og)
+ [Bitcoin Maximalism dataset](https://huggingface.co/datasets/LaierTwoLabsInc/BitcoinMaximalism)
 
 
 ### Results