Update README.md

README.md

@@ -11,7 +11,7 @@ language:
 - **Model Size:** 0.5B parameters
 - **Model Type:** Instruction-following Language Model
 - **Training Data**: About 700 high quality preference entries annotated by GPT-4.
-- **Training Procedure**: The DPO-Positive algorithm introduced abacusai was used to train this model.
+- **Training Procedure**: The DPO-Positive algorithm introduced by abacusai was used to train this model.
 
 ## Model Use
 tau-instruct-0.5B-DPOP is an instruction-following language model designed to follow user instructions and provide assistance across a wide range of tasks, including but not limited to: