app.py

import gradio as gr
import torch
from peft import PeftModel, PeftConfig

def greet(name):
    return "Hello " + name + "!!"

def model_run():
    peft_model_id = f"IThinkUPC/SQLGenerator-AI"
    config = PeftConfig.from_pretrained(peft_model_id)
    model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
    tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
    # Load the Lora model
    model = PeftModel.from_pretrained(model, peft_model_id)
    

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