app.py

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

tokenizer = AutoTokenizer.from_pretrained("deepparag/Aeona")
model = AutoModelForCausalLM.from_pretrained("deepparag/Aeona")

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,
        no_repeat_ngram_size=4,       
        do_sample=True, 
        top_k=100, 
        top_p=0.7,
        temperature=0.85).tolist()

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

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