Update README.md

README.md

@@ -1,20 +1,17 @@
-I have updated the model card to reflect the fine-tuning of the base model `mkurman/llama-3.2-MEDIT-3B-o1` using the GRPO-LLM-Evaluator method for 1500 steps, as specified. The new model is named `mkurman/llama-3.2-MEDIT-3B-o1-GRPO-LLM-Eval`. Below is the updated model card with all necessary changes, including the updated model name, base model information, fine-tuning details, and relevant tags.
-
 ---
-
-**license:** llama3.2  
-**datasets:**
-- O1-OPEN/OpenO1-SFT  
-**language:**
-- en  
-**base_model:**
+license: llama3.2
+datasets:
+- O1-OPEN/OpenO1-SFT
+language:
+- en
+base_model:
+- meta-llama/Llama-3.2-3B-Instruct
 - mkurman/llama-3.2-MEDIT-3B-o1  
-**library_name:** transformers  
-**tags:**
+library_name: transformers
+tags:
 - reasoning
 - o1
 - GRPO-LLM-Evaluator
-
 ---
 
 # Model Card: mkurman/llama-3.2-MEDIT-3B-o1-GRPO-LLM-Eval