gpt-2模型训练后应用

一、生成的文件集：

根据上篇文章训练后的数据进行训练后，使用训练好的数据集：

二、代码样例实现：

from transformers import GPT2Tokenizer, GPT2LMHeadModel


tokenizer = GPT2Tokenizer.from_pretrained('./gpt2-model')
model = GPT2LMHeadModel.from_pretrained('./gpt2-model')

tokenizer.save_pretrained('./results/tokenizer')
model.save_pretrained('./results/model')

# 加载训练好的模型和tokenizer
tokenizer = GPT2Tokenizer.from_pretrained('./results/tokenizer')
model = GPT2LMHeadModel.from_pretrained('./results/model')

# 生成回答示例
question = "什么是高血压的最佳治疗方法？"
input_text = f"提问: {question}\n回答:"
input_ids = tokenizer.encode(input_text, return_tensors='pt')

output = model.generate(input_ids, max_length=100, top_k=50, top_p=0.95, temperature=0.7, do_sample=True)
answer = tokenizer.decode(output[0], skip_special_tokens=True).split("回答:")[1].strip()

print("问题:", question)
print("回答:", answer)