app.py

import transformers
import gradio as gr
import torch

from transformers import GPT2LMHeadModel, GPT2Tokenizer

tokenizer = GPT2Tokenizer.from_pretrained('dennis-fast/DialoGPT-ElonMusk')
model = GPT2LMHeadModel.from_pretrained('dennis-fast/DialoGPT-ElonMusk')

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=200,
                            pad_token_id=tokenizer.eos_token_id,
                            no_repeat_ngram_size=3,
                            #do_sample=True,
                            #top_k=100,
                            top_p=0.9,
                            temperature = 0.8
                            ).tolist()

    # convert the tokens to text, and then split the responses into the right format
    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,
             theme="default",
             css=".footer {display:none !important}",
             inputs=["text", "state"],
             examples=[['Hi, please introduce yourself.'],['Where do you live?'],['What is meaning of life?'],['Should I buy Dogecoin?']],
             outputs=["chatbot", "state"]).launch()