在笔记本电脑上解锁DeepSeek RB - 体验我测试过的最聪明的AI模型！

(venv) $ python deepseek.py

enter your question (or 'quit' to exit): a bat and a ball costs 1 dollar and 10 cents in total. the bat costs 1 dollar more than a ball. how much does the ball costs?

response: question: a bat and a ball costs 1 dollar and 10 cents in total. the bat costs 1 dollar more than a ball. how much does the ball costs?
answer: 5 cents.

... (后续推理过程) ...

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

def setup_model():
    model_id = "deepseek-ai/deepseek-r1-distill-qwen-7b"
    tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(
        model_id,
        torch_dtype=torch.float16,
        device_map="auto",
        trust_remote_code=True
    )
    return model, tokenizer

def generate_response(model, tokenizer, prompt, max_length=512):
    inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True).to(model.device)
    with torch.no_grad():
        outputs = model.generate(
            inputs.input_ids,
            attention_mask=inputs.attention_mask,
            max_length=max_length,
            temperature=0.7,
            top_p=0.9,
            do_sample=True,
            pad_token_id=tokenizer.pad_token_id,
        )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

def main():
    try:
        model, tokenizer = setup_model()
        while True:
            question = input("\nenter your question (or 'quit' to exit): ")
            if question.lower() == 'quit':
                break
            prompt = f"question: {question}\nanswer:"
            response = generate_response(model, tokenizer, prompt)
            print(f"\nresponse: {response}")
    except Exception as e:
        print(f"an error occurred: {str(e)}")

if __name__ == "__main__":
    main()