python src/transformers/models/flamingo/converting_flamingo_to_hf.py \
    --old_ckpt_path /path/to/open/flamingo/weights \
    --new_hf_path /output/path

model = transformers.FlamingoForConditionalGeneration.from_pretrained("/output/path")

import requests
import torch
import transformers
from PIL import Image

tokenizer = model.text_tokenizer
image_processor = transformers.CLIPImageProcessor()
demo_image_one = Image.open(
    requests.get(
        "http://images.cocodataset.org/val2017/000000039769.jpg", stream=True
    ).raw
)
demo_image_two = Image.open(
    requests.get(
        "http://images.cocodataset.org/test-stuff2017/000000028137.jpg", stream=True
    ).raw
)
query_image = Image.open(
    requests.get(
        "http://images.cocodataset.org/test-stuff2017/000000028352.jpg", stream=True
    ).raw
)
vision_x = (
    image_processor.preprocess(
        [demo_image_one, demo_image_two, query_image], return_tensors="pt"
    )["pixel_values"]
    .unsqueeze(1)
    .unsqueeze(0)
)
model.text_tokenizer.padding_side = "left"
lang_x = tokenizer(
    ["<image>An image of two cats.<|endofchunk|><image>An image of a bathroom sink.<|endofchunk|><image>An image of"],
    return_tensors="pt",
)

generated_text = model.generate(
    vision_x=vision_x,
    lang_x=lang_x["input_ids"],
    attention_mask=lang_x["attention_mask"],
    max_new_tokens=20,
    num_beams=3,
)

print("Generated text: ", model.text_tokenizer.decode(generated_text[0]))