metadata

datasets:
  - google/DOCCI
language:
  - en
library_name: peft
tags:
  - florence-2
  - lora
  - adapter
  - image-captioning
  - peft
model-index:
  - name: Florence-2-DOCCI-FT
    results:
      - task:
          type: image-to-text
          name: Image Captioning
        dataset:
          name: foundation-multimodal-models/DetailCaps-4870
          type: other
        metrics:
          - type: meteor
            value: 0.267
          - type: bleu
            value: 0.185
          - type: cider
            value: 0.086
          - type: capture
            value: 0.576
          - type: rouge-l
            value: 0.287

Florence-2 DOCCI-FT LoRA Adapter

This repository contains a LoRA adapter trained on google/docci for the Florence-2-base-FT model. It's designed to enhance the model's captioning capabilities, providing more detailed captions.

Usage

To use this LoRA adapter, you'll need to load it along with the Florence-2-base model using the PEFT library. Here's an example of how to use it:

from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM
from peft import PeftModel, PeftConfig
import requests

def caption(image):
  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)
  prompt = "<MORE_DETAILED_CAPTION>"
  adapter_name = "NikshepShetty/Florence-2-DOCCI-FT"
  model = PeftModel.from_pretrained(base_model, adapter_name, trust_remote_code=True)
  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,
      do_sample=False,
      num_beams=3
  )
  generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

  parsed_answer = processor.post_process_generation(generated_text, task="<MORE_DETAILED_CAPTION>", image_size=(image.width, image.height))

  print(parsed_answer)

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)
caption(image)

This code demonstrates how to:

Load the base Florence-2 model
Load the LoRA adapter
Process an image and generate a detailed caption

Note: Make sure you have the required libraries installed: transformers, peft, einops, flash_attn, timm, Pillow, and requests.

Evaluation results

Our LoRA adapter shows improvements over the base Florence-2 model across all metrics for MORE_DETAILED_CAPTION tag for 1000 images on the foundation-multimodal-models/DetailCaps-4870 dataset:

Metric	Base Model	Adapted Model	Improvement
CAPTURE	0.546	0.576	+5.5%
METEOR	0.213	0.267	+25.4%
BLEU	0.110	0.185	+68.2%
CIDEr	0.031	0.086	+177.4%
ROUGE-L	0.275	0.287	+4.4%

These results demonstrate that our LoRA adapter enhances the image captioning capabilities of the Florence-2 base model, particularly in generating more detailed and accurate captions.