app.py

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

title = "Custom AI ChatBot"
description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
examples = [["How are you?"]]

tokenizer = AutoTokenizer.from_pretrained("william4416/bewtestingone")
model = AutoModelForCausalLM.from_pretrained("william4416/bewtestingone")

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=4000, pad_token_id=tokenizer.eos_token_id
    ).tolist()

    # convert the tokens to text
    response = tokenizer.decode(history[0])
    return response, history

def main():
    gr.Interface(
        fn=predict,
        title=title,
        description=description,
        examples=examples,
        inputs=["text", "state"],
        outputs=["text", "state"],
        theme="finlaymacklon/boxy_violet",
    ).launch()

if __name__ == "__main__":
    main()