使用Huggingface Transformers的聊天机器人

Question

我想用Huggingface Transformers来实现一个聊天机器人。目前，我的代码如下所示。转换器模型已经考虑了过去用户输入的历史。

在构建聊天机器人时，我还需要考虑其他因素(额外的代码)吗？

其次，如何修改代码以使用TensorFlow而不是PyTorch运行？

稍后，我还计划对其他数据的模型进行微调。我还计划测试不同的模型，比如BlenderBot和GPT2。我认为要测试这些不同的模型，应该和替换AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")和AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")中的相应模型一样简单

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

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

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)))

Answer 1

下面是在Tensorflow中使用DialoGPT模型的一个示例：

from transformers import TFAutoModelForCausalLM, AutoTokenizer, BlenderbotTokenizer, TFBlenderbotForConditionalGeneration
import tensorflow as tf

chat_bots = {
    'BlenderBot': [BlenderbotTokenizer.from_pretrained('facebook/blenderbot-400M-distill'), TFT5ForConditionalGeneration.from_pretrained('facebook/blenderbot-400M-distill')],
    'DialoGPT': [AutoTokenizer.from_pretrained("microsoft/DialoGPT-small"), TFAutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")],
} 
key = 'DialoGPT'
tokenizer, model = chat_bots[key]

for step in range(5):
    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='tf')
    if step > 0:
      bot_input_ids = tf.concat([chat_history_ids, new_user_input_ids], axis=-1)  
    else:
      bot_input_ids = new_user_input_ids

    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)

    print(key + ": {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))

>> User:How are you?
DialoGPT: I'm here
>> User:Why are you here
DialoGPT: I'm here
>> User:But why
DialoGPT: I'm here
>> User:Where is here
DialoGPT: Where is where?
>> User:Here
DialoGPT: Where is here?

如果你想比较不同的聊天机器人，你可能想要调整它们的解码器参数，因为它们并不总是相同的。例如，使用BlenderBot和max_length 50，您会得到当前代码的这种响应：

>> User:How are you?
BlenderBot: ! I am am great! how how how are are are???

一般来说，你应该问问自己，对于聊天机器人来说，哪些特殊字符是重要的(取决于您的域)，哪些字符应该/可以省略？

您还应该尝试不同的解码方法，如贪婪搜索、波束搜索、随机采样、top-k采样和核采样，并找出最适合您的用例的解码方法。有关此主题的更多信息，请查看此post