app.py

import gradio as gr
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_path = "HuggingFaceTB/SmolVLM2-2.2B-Instruct"
processor = AutoProcessor.from_pretrained(model_path)
model = AutoModelForImageTextToText.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    _attn_implementation="flash_attention_2"
).to("cuda")

def launch(input):
    out = model.generate(**input)
    return(out)

iface = gr.Interface(launch,
                     inputs=gr.Image(type='pil'),
                     outputs="text")

iface.launch()