app.py

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

# 加载 DeepSeekMath 模型和分词器
model_name = "deepseek-ai/deepseek-math-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

# 定义带有链式推理的数学问题
messages = [
    {"role": "user", "content": "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \\boxed{}."}
]

# 将问题转换为模型输入格式
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

# 生成模型的输出
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)

# 解码输出并打印结果
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)