demo_chatbot_gpt.py

# coding=utf-8
# author: xusong <xusong28@jd.com>
# time: 2022/8/25 16:57

"""

https://gradio.app/creating_a_chatbot/

https://huggingface.co/spaces/abidlabs/chatbot-stylized/blob/main/app.py

"""

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import gradio as gr

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


def predict(input, history=[]):
    # tokenize the new input sentence
    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)

    # generate a response
    history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()  # gpt2生成结果会拼接上输入。

    # convert the tokens to text, and then split the responses into lines
    response = tokenizer.decode(history[0]).split("<|endoftext|>")
    response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list
    return response, history




gr.Interface(fn=predict,
             inputs=["text", "state"],
             outputs=["chatbot", "state"]).launch()