Update README.md

README.md

@@ -13,29 +13,8 @@ language:
 # Qwen2.5-3B-GRPO-MATH-1EPOCH
 
 **Description:**  
-A GRPO-fine-tuned version of Qwen2.5-3B-Instruct trained on the MATH dataset. It is optimized to produce more accurate contest-style math solutions.
 
----
-
-## Usage
-
-```python
-from transformers import pipeline
-
-generator = pipeline(
-    "text-generation",
-    model="USERNAME/Qwen-2.5-3B-GRPO-Math",
-    device="cuda"
-)
-
-prompt = "Evaluate the integral ∫₀¹ x² dx."
-result = generator(
-    [{"role": "user", "content": prompt}],
-    max_new_tokens=50,
-    return_full_text=False
-)[0]
-print(result["generated_text"])
-````
+A GRPO-fine-tuned version of Qwen2.5-3B trained on the MATH dataset.
 
 ---