my-gemma-space/app.py

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

# Model otomatik Hugging Face'den indirilecek
model_name = "google/gemma-2-2b-it"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=generate, 
    inputs="text", 
    outputs="text",
    title="Gemma 2-2B IT - CPU Friendly",
    description="API endpoint üzerinden otomasyon ve text generation için kullanılabilir."
)

iface.launch()