app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr

# Load the model and tokenizer
model_name = "microsoft/DialoGPT-small"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Function to generate a response
def dialoGPT_response(user_input, history):
    # Encode the new user input, with the history
    new_user_input_ids = tokenizer.encode(user_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) if history else new_user_input_ids

    # Generate a response
    chat_history_ids = model.generate(
        bot_input_ids, 
        max_length=1000,
        pad_token_id=tokenizer.eos_token_id
    )

    # Decode the response
    response = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
    return response

# Gradio interface
iface = gr.Interface(
    fn=dialoGPT_response,
    inputs=[gr.Textbox(placeholder="Enter your message..."), "state"],
    outputs="text",
    title="DialoGPT Chat",
    description="Chat with DialoGPT-small model."
)

iface.launch()