Update README.md

README.md

@@ -1,3 +1,16 @@
+---
+license: mit
+datasets:
+- tuandunghcmut/normal_dataset
+language:
+- en
+metrics:
+- accuracy
+- perplexity
+base_model:
+- unsloth/Qwen2.5-Coder-1.5B-Instruct
+pipeline_tag: text-generation
+---
 # Using Unsloth to Load and Run Qwen25_Coder_MultipleChoice
 
 Unsloth offers significant inference speed improvements for the Qwen25_Coder_MultipleChoice model. Here's how to properly load and use the model with Unsloth:
@@ -140,19 +153,20 @@ def get_answer(question, choices, model, tokenizer):
     }
 
 # Example usage
-python_example = {
-    "question": "Which of the following correctly defines a list comprehension in Python?",
+java_example = {
+    "question": "Which of the following correctly creates a new instance of a class in Java?",
     "choices": [
-        "[x**2 for x in range(10)]",
-        "for(x in range(10)) { return x**2; }",
-        "map(lambda x: x**2, range(10))",
-        "[for x in range(10): x**2]"
-    ]
+        "MyClass obj = new MyClass();",
+        "var obj = MyClass();",
+        "MyClass obj = MyClass.new();",
+        "obj = new(MyClass);"
+    ],
+    "answer": "A"  # Optional ground truth
 }
 
 result = get_answer(
-    python_example["question"], 
-    python_example["choices"],
+    java_example["question"], 
+    java_example["choices"],
     model,
     tokenizer
 )
@@ -254,4 +268,4 @@ def batch_process_questions(questions_list, model, tokenizer, batch_size=4):
    pip install flash-attn --no-build-isolation
    ```
 
-With these optimizations, Qwen25_Coder_MultipleChoice should run significantly faster while maintaining the same high-quality multiple-choice reasoning and answers.
+With these optimizations, Qwen25_Coder_MultipleChoice should run significantly faster while maintaining the same high-quality multiple-choice reasoning and answers.