microsoft

/

Florence-2-large-ft

like 385

Follow

Microsoft 19.9k

Seems like the same problem as: https://huggingface.co/microsoft/phi-1_5/discussions/72

I'm trying the provided workaround with modeling_florence2.py (still downloading the model it didn't crash so far):

import os
from unittest.mock import patch

import requests
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor
from transformers.dynamic_module_utils import get_imports


def fixed_get_imports(filename: str | os.PathLike) -> list[str]:
    """Work around for https://huggingface.co/microsoft/phi-1_5/discussions/72."""
    if not str(filename).endswith("/modeling_florence2.py"):
        return get_imports(filename)
    imports = get_imports(filename)
    imports.remove("flash_attn")
    return imports


with patch("transformers.dynamic_module_utils.get_imports", fixed_get_imports):

    model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large-ft", trust_remote_code=True)
    processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large-ft", trust_remote_code=True)

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)

def run_example(prompt):

    inputs = processor(text=prompt, images=image, return_tensors="pt")
    generated_ids = model.generate(
    input_ids=inputs["input_ids"],
    pixel_values=inputs["pixel_values"],
    max_new_tokens=1024,
    num_beams=3,
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

    parsed_answer = processor.post_process_generation(generated_text, task=prompt, image_size=(image.width, image.height))

    print(parsed_answer)

prompt = "<MORE_DETAILED_CAPTION>"
run_example(prompt)

Edit: With this workaround, it works on my MacBook!