Update README.md

README.md

@@ -12,7 +12,7 @@ widget:
 
 # Qwen1.5-0.5B-Chat with EPFL DPO fine-tuning
 
-Qwen1.5-0.5B-Chat DPO fine-tuned on the microsoft/orca-math-word-problems-200k dataset that consists of ~200K grade school math word problems
+Qwen1.5-0.5B-Chat DPO fine-tuned on the Orca Math dataset that consists of ~200K grade school math word problems
 
 ## Model Details
 
@@ -29,7 +29,7 @@ answer open-ended and multiple-choice questions from Orca Math dataset
 
 ### Training Data
 
-Training data is not publicly available.
+HuggingFace dataset : microsoft/orca-math-word-problems-200k
 
 ### Training Procedure