app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "dleemiller/Penny-1.7B"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint)

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

gr.Interface(fn=generate_response, inputs="text", outputs="text").launch()