Update README.md

README.md

@@ -12,15 +12,26 @@ tags:
 
 * **Model size: 3.21B parameters**
 
-# **WARNING**
+# **V2**
 
 **This version is a further fine-tuned version of Llama-3.2-3B-Instruct with a slightly larger dataset and more epochs.**
 
-**It has been not tested for stability or performance.**
+**The V2 version performs better in multiple benchmarks than the V1 version, and even outmatches both 1211 and V1 in mathematics: https://huggingface.co/MultivexAI/Gladiator-Mini-Exp-1221-3B-Instruct**
 
-**It's performance and stability may vary significantly.**
+**Examples:**
 
-**More stable version: https://huggingface.co/MultivexAI/Gladiator-Mini-Exp-1221-3B-Instruct**
+**MATH**
+**1211: 13.44 %**
+**V1: 13.07 %**
+**V2: 13.75 %**
+
+**IFEval**
+**V1: 60.79 %**
+**V2: 62.15 %**
+
+**BBH**
+**V1: 20.40 %** 
+**V2: 20.65 %**
 
 # Gladiator-Mini-exp-1221-Instruct