import requests
import torch
import sys
from PIL import Image
from transformers import MllamaForConditionalGeneration, AutoProcessor

import os
os.environ['TRANSFORMERS_CACHE'] = '/var/www/.cache/huggingface/hub/'
os.environ['HF_TOKEN'] = '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'



model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"

model = MllamaForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto" 
)
processor = AutoProcessor.from_pretrained(model_id)

#url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
url   = sys.argv[1]
inp_text_arg = sys.argv[2]
image = Image.open(requests.get(url, stream=True).raw)

messages = [
    {"role": "user", "content": [
        {"type": "image"},
        {"type": "text", "text": inp_text_arg }
    ]}
]
input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(
    image,
    input_text,
    add_special_tokens=False,
    return_tensors="pt"
).to(model.device)

output = model.generate(**inputs, max_new_tokens=200)
print(processor.decode(output[0]))