app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
from PIL import Image
import requests

# Load the processor
processor = AutoProcessor.from_pretrained(
    'allenai/Molmo-7B-D-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

# Load the model
model = AutoModelForCausalLM.from_pretrained(
    'allenai/Molmo-7B-D-0924',
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

def describe_image(image):
    # Process the image and text
    inputs = processor.process(
        images=[image],
        text='''an image of a human sitting properly , with a laptop/pc clearly visible and the student’s face at least 40%-50% visible. The student should be looking at the laptop screen with both hands on the keyboard. There should be no other accessories other than laptop/pc, and no other second person should be present ." // analyse image on this conditions // if all condition satisfied answer YES else NO// Answer only in YES or NO'''
    )
    
    # Move inputs to the correct device and make a batch of size 1
    inputs = {k: v.to(model.device).unsqueeze(0) for k, v in inputs.items()}

    # Generate output; maximum 200 new tokens; stop generation when <|endoftext|> is generated
    output = model.generate_from_batch(
        inputs,
        GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
        tokenizer=processor.tokenizer
    )

    # Only get generated tokens; decode them to text
    generated_tokens = output[0, inputs['input_ids'].size(1):]
    generated_text = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True)

    return generated_text

# Create the Gradio interface
iface = gr.Interface(
    fn=describe_image,
    inputs=gr.Image(type="pil", label="Upload an Image"),
    outputs=gr.Textbox(label="Description"),
    title="OPPE",
    description="OPPE VERRFICATION."
)

# Launch the interface
iface.launch()