app.py

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

# tokenizer = AutoTokenizer.from_pretrained("chavinlo/gpt4-x-alpaca")
# model = AutoModelForCausalLM.from_pretrained("chavinlo/gpt4-x-alpaca")

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


with gr.Blocks() as demo:
    chatbot = gr.Chatbot()
    msg = gr.Textbox()
    clear = gr.Button("Clear")

    def user(user_message, history):
        return "", history + [[user_message, None]]

    def bot(history):
        user_message = history[-1][0]
        new_user_input_ids = tokenizer.encode(user_message + 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()

        # 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

        # Add the new response to the chat history
        history = history + [tokenizer.encode(response[0][0] + tokenizer.eos_token, return_tensors='pt')]

        return history


    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
        bot, chatbot, chatbot
    )
    clear.click(lambda: None, None, chatbot, queue=False)

demo.launch()