app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base + finetuned model
base_model = "unsloth/Phi-3-mini-4k-instruct-bnb-4bit"
finetuned_model = "saadkhi/SQL_Chat_finetuned_model"

tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model)
model = PeftModel.from_pretrained(model, finetuned_model)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="SQL Chatbot")
iface.launch()