Update README.md

README.md

@@ -86,10 +86,23 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
 1. Don't include a system prompt; instead, place all instructions directly in the user prompt.
 2. We recommend using the following instruction for math questions: Please reason step by step, and put your final answer within \\boxed{}. 
-3. We recommend using the following instruction for code questions: Write Python code to solve the problem. Please place the solution code in the following format:\\n
-\`\`\`python\\n
-\# Your solution code here\\n
-\`\`\`
+3. We recommend using the following instruction for code questions:
+```python
+question = "" # code question
+starter_code = "" # starter code function header
+
+code_instruction_nostartercode = """Write Python code to solve the problem. Please place the solution code in the following format:\n```python\n# Your solution code here\n```"""
+code_instruction_hasstartercode = """Please place the solution code in the following format:\n```python\n# Your solution code here\n```"""
+if starter_code != "":
+    question += "\n\n" + "Solve the problem starting with the provided function header.\n\nFunction header:\n" + "```\n" + starter_code + "\n```"
+    question += "\n\n" + code_instruction_hasstartercode
+else:
+    question += "\n\n" + code_instruction_nostartercode
+
+final_prompt = "<｜User｜>" + question + "<｜Assistant｜><think>\n"
+```
+5. Our inference engine for evaluation is **vLLM==0.7.3** using top-p=0.95, temperature=0.6, max_tokens=32768.
+6. We use [AceMath scorer](https://huggingface.co/nvidia/AceMath-7B-Instruct/blob/main/evaluation/grader.py) for math evaluation and [LiveCodeBench official script](https://github.com/LiveCodeBench/LiveCodeBench) for code evaluation.
 
 
 ## Correspondence to