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

model_name_or_path = "bigscience/bloom"  # النموذج المقترح
device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path).to(device).eval()

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=200,
            do_sample=True,
            top_p=0.9,
            temperature=0.8
        )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(lines=4, placeholder="اكتب سؤالك هنا..."),
    outputs="text",
    title="BLOOM Text Generator",
    description="قم بإدخال نص وسيقوم النموذج بتوليد نص مكمل أو إجابة."
)

iface.launch()