app.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr

model_id = "moatamed8/test_product-model"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)

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

demo = gr.Interface(infer, "text", "text")
demo.launch()