app.py

from transformers import AutoModelWithLMHead, AutoTokenizer
import gradio as gr


tokenizer = AutoTokenizer.from_pretrained('microsoft/DialoGPT-small', padding_side='right')
model = AutoModelWithLMHead.from_pretrained('tomkr000/scottbotai')


def chat(message, history=[]):
            
    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors="pt")
                
    reply_ids = model.generate(
                        inputs, max_length=1000,
                        pad_token_id=tokenizer.eos_token_id,  
                        no_repeat_ngram_size=3,       
                        do_sample=True, 
                        top_k=100, 
                        top_p=0.7,
                        temperature = 0.8
                        )
        
    response = tokenizer.decode(reply_ids[:,inputs.shape[1]:][0], skip_special_tokens=True)
        
    history.append((message, response))
    
    return history, history
         

# chatbot = gr.Chatbot().style(color_map=("green", "pink"))

demo = gr.Interface(
    fn=chat,
    inputs = ["text", "state"],
    outputs = ['chatbot', "state"],
    allow_flagging="never",
        ).launch()