Florence 2 Base Gpt4 Captioner V1

🚀 GPT4-O Style Image Captioner

A fine-tuned model based on microsoft/Florence-2-base-ft for generating GPT4-O style image captions.

🚀 Quick Start

✨ Features

• This model can generate GPT4-O style captions for images.
• It is a fine-tuned version using microsoft/Florence-2-base-ft.

📦 Installation

No specific installation steps provided in the original document.

💻 Usage Examples

Basic Usage

# Load fine-tuned model and processor
import torch
from transformers import AutoModelForCausalLM, AutoProcessor
from PIL import Image

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
repo_name = "Vimax97/Florence-2-base-gpt4_captioner_v1" 
model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained(repo_name, trust_remote_code=True)

# Inference
image = Image.open("<path_to_image>")
prompt = "<ImageCAP>" + 'What is the <GPT4> style description for this image?'

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,
    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=prompt, image_size=(image.width, image.height))

print("Generated: ",parsed_answer[prompt])

📚 Documentation

Uses

This is a GPT4-O Style captioner, a fine-tuned version using florence-2-base-ft.

Direct Use

This model can be used to create GPT4-O style captions.

Out-of-Scope Use

• This model might not generate long-text descriptions as the context length is 1024.
• Linear scaling is applied to increase the context length, its effect was not measured!

Training Hyperparameters

• Training regime: fp32 precision, 1000 images were used, 1 epoch of finetuning

📄 License

This model is licensed under the MIT license.