探索面向开放型问题的推理模型Marco-o1，阿里国际AI团队最新开源！

Begin by split the task into serval sub-tasks within <sub-task> tags, then enclosing all thoughts within <thinking> tags, exploring multiple angles andContinuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress.The hypothesis is presented within <hypothesis>.Regularly evaluate progress using <reflection> tags.Be critical and honest about your reasoning process.If unsure, backtrack and try a different approach, explaining your decision within <thinking> tags.Output should be markdown format and tags can not nested.   For mathematical problems, show all work explicitly using LaTeX for formal notation and provide detailed proofs.Explore multiple solutions individually if possible, comparing approaches in reflections.Use thoughts as a scratchpad, writing out all calculations and reasoning explicitly.Synthesize the final answer within <answer> tags, providing a clear, concise summary.Conclude with a final reflection on the overall solution, discussing effectiveness, challenges, and solutions.\n\nNow the Question is:\n4只小鸭子在一个大的圆形水池中，分别随机的出现在圆圈中的任意一点。4只鸭子出现在 同一半圆的概率是多少？

import torch
from typing import List, Dict, Tuple
from modelscope import AutoModelForCausalLM, AutoTokenizer

def load_model_and_tokenizer(path):
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(path, trust_remote_code=True).to('cuda:0')
    model.eval()
    return tokenizer, model

def generate_response(model, tokenizer,
                      input_ids, attention_mask,
                      max_new_tokens=4096):
    generated_ids = input_ids
    with torch.inference_mode():
        for _ in range(max_new_tokens):
            outputs = model(input_ids=generated_ids, attention_mask=attention_mask)
            next_token_id = torch.argmax(outputs.logits[:, -1, :], dim=-1).unsqueeze(-1)
            generated_ids = torch.cat([generated_ids, next_token_id], dim=-1)
            attention_mask = torch.cat([attention_mask, torch.ones_like(next_token_id)], dim=-1)
            new_token = tokenizer.decode(next_token_id.squeeze(), skip_special_tokens=True)
            print(new_token, end='', flush=True)
            if next_token_id.item() == tokenizer.eos_token_id:
                break
                return tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], 
                                        skip_special_tokens=True)

def chat(model, tokenizer):
    history: List[Dict[str, str]] = []
    print("Enter 'q' to quit, 'c' to clear chat history.")
    while True:
        user_input = input("User: ").strip().lower()
        if user_input == 'q':
            print("Exiting chat.")
            break
            if user_input == 'c':
                print("Clearing chat history.")
                history.clear()
                continue
                if not user_input:
                    print("Input cannot be empty.")
                    continue
        history.append({"role": "user", "content": user_input})
        text = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
        model_inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=4096).to('cuda:0')
        print('Assistant:', end=' ', flush=True)
        response = generate_response(model, tokenizer, model_inputs.input_ids, model_inputs.attention_mask)
        print()
        history.append({"role": "assistant", "content": response})

def main():
    path = "AIDC-AI/Marco-o1"
    tokenizer, model = load_model_and_tokenizer(path)
    print('Starting chat.')
    chat(model, tokenizer)

if __name__ == "__main__":
    main()