模型:

model-attribution-challenge/DialoGPT-large

英文

一个最新的大规模预训练对话生成模型(DialoGPT)

DialoGPT是一个最新的大规模预训练对话生成模型,用于多轮对话。 human evaluation results 表明DialoGPT生成的回复在单轮对话图灵测试下与人类回复质量相当。该模型是使用来自Reddit讨论主题的147M多轮对话进行训练的。

  • 来自交互环境的多轮生成示例:
Role Response
User Does money buy happiness?
Bot Depends how much money you spend on it .
User What is the best way to buy happiness ?
Bot You just have to be a millionaire by your early 20s, then you can be happy .
User This is so difficult !
Bot You have no idea how hard it is to be a millionaire and happy . There is a reason the rich have a lot of money

请查看关于DialoGPT的预处理、训练和详细信息的 original DialoGPT repository

ArXiv论文: https://arxiv.org/abs/1911.00536

如何使用

现在我们可以尝试一下将该模型作为交谈伙伴的工作方式!

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch


tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")

# Let's chat for 5 lines
for step in range(5):
    # encode the new user input, add the eos_token and return a tensor in Pytorch
    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids

    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)

    # pretty print last ouput tokens from bot
    print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))