app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

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

# Define the function to generate responses
def respond_to_input(user_input):
    inputs = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
    reply_ids = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
    reply = tokenizer.decode(reply_ids[:, inputs.shape[-1]:][0], skip_special_tokens=True)
    return reply

# Create the Gradio interface
iface = gr.Interface(fn=respond_to_input, inputs="text", outputs="text")

# Launch the app
iface.launch()