app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr

model_id = "EleutherAI/gpt-neo-125M"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

def gera_texto(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    out = model.generate(**inputs, max_length=100)
    return tokenizer.decode(out[0], skip_special_tokens=True)

iface = gr.Interface(fn=gera_texto,
                     inputs="text",
                     outputs="text",
                     title="GPT-Neo 125M Demo")
iface.launch()