app.py

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

# Load model and tokenizer
model_name = "AhmedBAH/DesertMind"  # Your fine-tuned model path
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float32,
    device_map={'': 'cpu'},
    use_cache=False
)

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(**inputs, max_new_tokens=50, do_sample=True, temperature=0.1)
    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response

# Gradio Interface
iface = gr.Interface(
    fn=generate_text,
    inputs="text",
    outputs="text",
    title="🚀 Fine-tuned Model Demo",
    description="Enter a prompt to generate text using your fine-tuned model."
)

iface.launch()