app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import modin as pd
import gradio as gr
tokenizer = AutoTokenizer.from_pretrained("microsoft/lts-gpt2-sm")
model = AutoModelForCausalLM.from_pretrained("microsoft/lts-gpt2-sm", subfolder="gpt2_6c6e63116ff74ba444ff5a08cef54380073ebea3")

attention_mask = {'pad_token_id':1,
                  'eos_token_id':0}

def chat(Prompt):
    #input_ids = tokenizer(Prompt, return_tensors="pt").input_ids
    generated_ids = model.generate(Prompt, max_length=128)
    bot = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
    return bot
 

gr.Interface(fn=chat, inputs='text', outputs='text').launch(debug=True)