app.py

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

# Load your quantized model
model_name = "khaled123/hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)

def chat(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(inputs["input_ids"], max_length=150, num_return_sequences=1)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

iface = gr.Interface(fn=chat, 
                     inputs="text", 
                     outputs="text",
                     title="Chatbot",
                     description="A chatbot using a quantized model")

iface.launch()