generator2.py

import torch
from transformers import AutoProcessor, AutoModelForPreTraining

def response(image2, image):

    processor = AutoProcessor.from_pretrained("google/paligemma-3b-pt-224")
    model = AutoModelForPreTraining.from_pretrained("google/paligemma-3b-pt-224")
    
    # Instruct the model to create a caption in Spanish
    model_inputs = processor(text="check whether both molecules have the same chemical structure. if yes, output correct and if not, output incorrect", images= [image, image2], return_tensors="pt")
    input_len = model_inputs["input_ids"].shape[-1]

    with torch.inference_mode():
        generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
        generation = generation[0][input_len:]
        decoded = processor.decode(generation, skip_special_tokens=True)
    return decoded