Cogflorence 2.2 Large

🚀 microsoft/Florence-2-large tuned on Ejafa/ye-pop captioned with CogVLM2

This repository houses a fine - tuned version of the microsoft/Florence-2-large model. It has been optimized on a 40,000 - image subset of the Ejafa/ye-pop dataset. The captions for this tuning were generated by THUDM/cogvlm2-llama3-chat-19B, enhancing the model's image - to - text capabilities.

✨ Features

• Fine - tuned on a diverse image subset from Ejafa/ye-pop dataset.
• Captions are generated by THUDM/cogvlm2-llama3-chat-19B and refined by google/gemma-2-9b.
• Suitable for image - to - text tasks.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoProcessor, AutoConfig
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained("thwri/CogFlorence-2.2-Large", trust_remote_code=True).to(device).eval()
processor = AutoProcessor.from_pretrained("thwri/CogFlorence-2.2-Large", trust_remote_code=True)
# Function to run the model on an example
def run_example(task_prompt, image):
    prompt = task_prompt
    # Ensure the image is in RGB mode
    if image.mode != "RGB":
        image = image.convert("RGB")
    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,
        num_beams=3,
        do_sample=True
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
    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
import copy
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)
result = run_example("<MORE_DETAILED_CAPTION>" , image)
print(result)
# {'<MORE_DETAILED_CAPTION>': 'A vivid portrayal of a classic Volkswagen Beetle parked on a cobblestone street. The car is painted a vibrant turquoise, contrasting with the muted yellow of the building behind it. The building has two wooden doors, one with a white frame and the other with a dark brown finish. The sky is clear, and the sun casts a warm glow on the scene, highlighting the car's details. The image evokes a nostalgic and nostalgic mood, capturing a moment in time without posed elements.'}

📚 Documentation

Training Details

Dataset

The fine - tuning process made use of a 40,000 - image subset from the Ejafa/ye-pop dataset. This dataset offers a wide variety of images with different subjects, which serves as a solid training ground for enhancing the model's captioning capabilities.

Captioning

The captions were generated by THUDM/cogvlm2-llama3-chat-19B and then post - processed by google/gemma-2-9b to eliminate vagueness.

📄 License

This project is licensed under the MIT license.