app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "Abdul-Basit123/llama-3-8b-Instruct-bnb-4bit-finetuned"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)

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

iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="Model-Q Demo")
iface.launch()