开发基于ChatGPT的自动写作系统：Python释放创意

import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel
from torch.utils.data import Dataset, DataLoader

class TextDataset(Dataset):
    def __init__(self, data_path, tokenizer):
        self.tokenizer = tokenizer
        self.data = []
        with open(data_path, 'r', encoding='utf-8') as f:
            for line in f:
                line = line.strip()
                if line:
                    self.data.append(line)

    def __len__(self):
        return len(self.data)

    def __getitem__(self, index):
        text = self.data[index]
        input_ids = self.tokenizer.encode(text, add_special_tokens=True, truncation=True)
        return torch.tensor(input_ids, dtype=torch.long)

def collate_fn(data):
    input_ids = torch.stack([item for item in data])
    attention_mask = input_ids.ne(0).float()
    return {'input_ids': input_ids, 'attention_mask': attention_mask}

data_path = 'train.txt'
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2LMHeadModel.from_pretrained('gpt2')

dataset = TextDataset(data_path, tokenizer)
dataloader = DataLoader(dataset, batch_size=4, collate_fn=collate_fn, shuffle=True)

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)

optimizer = torch.optim.Adam(model.parameters(), lr=1e-5)

for epoch in range(5):
    total_loss = 0.0
    for batch in dataloader:
        batch = {k: v.to(device) for k, v in batch.items()}
        outputs = model(**batch, labels=batch['input_ids'])
        loss = outputs.loss
        total_loss += loss.item()
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    print('Epoch:', epoch, ' Loss:', total_loss)

def generate_text(model, tokenizer, prompt, max_length=100):
    input_ids = tokenizer.encode(prompt, add_special_tokens=True, truncation=True, return_tensors='pt')
    input_ids = input_ids.to(device)
    output = model.generate(input_ids, max_length=max_length, num_return_sequences=1)
    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
    return generated_text

prompt = '在一个阳光明媚的早晨，小明和小红走进了一家魔法书店，'
generated_text = generate_text(model, tokenizer, prompt)
print(generated_text)