import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "google/gemma-2-9b-it"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

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

iface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
iface.launch()