Mit1208/Florence-2-DocLayNet

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: [Mit Patel]
• Shared by [optional]: [Mit Patel]
• Finetuned from model [optional]: https://huggingface.co/microsoft/Florence-2-base-ft

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Inference Procedure

!pip install -qU transformers
!pip install -qU accelerate bitsandbytes einops flash_attn timm
!pip install -q datasets

from PIL import Image
import requests
import torch
from transformers import AutoProcessor, AutoModelForVision2Seq, BitsAndBytesConfig, TrainingArguments, AutoModelForCausalLM
import requests
import re
from transformers import AutoConfig, AutoProcessor, AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True,)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True,)
model = AutoModelForCausalLM.from_pretrained("Mit1208/Florence-2-DocLayNet", trust_remote_code=True, config = base_model.config)

def run_example(task_prompt, image, text_input=None):
    if text_input is None:
        prompt = task_prompt
    else:
        prompt = task_prompt + text_input
    print(prompt)
    inputs = processor(text=prompt, images=image, return_tensors="pt").to(device)
    generated_ids = model.generate(
      input_ids=inputs["input_ids"],
      pixel_values=inputs["pixel_values"],
      max_new_tokens=1024,
      early_stopping=False,
      do_sample=False,
      num_beams=3,
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
    print(generated_text)
    parsed_answer = processor.post_process_generation(
        generated_text,
        task=task_prompt,
        image_size=(image.width, image.height)
    )

    return parsed_answer

from PIL import Image
import requests

image = Image.open('form-1.png').convert('RGB')
task_prompt = '<OD>'
results = run_example(task_prompt, example['image'].resize(size=(1000, 1000)))
print(results)