Update Usage

README.md

@@ -60,10 +60,10 @@ We apply tailored prompts for coding and math task:
 
 
 ```python
+
 import os
 from tqdm import tqdm
 import torch
-from transformers import AutoTokenizer
 from vllm import LLM, SamplingParams
 os.environ["NCCL_IGNORE_DISABLED_P2P"] = "1"
 os.environ["TOKENIZERS_PARALLELISM"] = "true"
@@ -82,27 +82,25 @@ def generate(question_list,model_path):
     completions = [[output.text for output in output_item.outputs] for output_item in outputs]
     return completions
 
-def make_conv_hf(question, tokenizer):
-    # for math problem
-    content = question + "\n\nPresent the answer in LaTex format: \\boxed{Your answer}"
-    # for code problem
-    # content = question + "\n\nWrite Python code to solve the problem. Present the code in \n```python\nYour code\n```\nat the end." 
-    msg = [
-        {"role": "user", "content": content}
-    ]
-    chat = tokenizer.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
-    return chat
-    
+
+def make_conv_zero(question):
+    question = question + "\n\nPresent the answer in LaTex format: \\boxed{Your answer}"
+    content = f"A conversation between User and Assistant. The user asks a question, and the Assistant solves it. The assistant first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>. User: {question}. Assistant:"
+    print(content)
+    return content
+
 def run():
     model_path = "PRIME-RL/Eurus-2-7B-PRIME-Zero"
     all_problems = [
         "which number is larger? 9.11 or 9.9?"
     ]
-    tokenizer = AutoTokenizer.from_pretrained(model_path)
-    completions = generate([make_conv_hf(problem_data, tokenizer) for problem_data in all_problems],model_path)
+    completions = generate([make_conv_zero(problem_data) for problem_data in all_problems],model_path)
     print(completions)
+    # " Let's compare the numbers 9.11 and 9.9.\n\nTo determine which number is larger, we can compare them digit by digit from left to right.\n\nFirst, let's look at the digits in the ones place:\n- Both numbers have a 9 in the ones place.\n\nNext, let's look at the digits in the tenths place:\n- The number 9.11 has a 1 in the tenths place.\n- The number 9.9 has a 9 in the tenths place.\n\nSince 9 is greater than 1, we can conclude that 9.9 is greater than 9.11.\n\nSo, the larger number is \\(\\boxed{9.9}\\)."
 if __name__ == "__main__":
     run()
+
+
 ```