---
license: apache-2.0
datasets:
- eltorio/ROCO-radiology
language:
- en
base_model:
- HuggingFaceM4/Idefics3-8B-Llama3
pipeline_tag: image-text-to-text
library_name: peft
---

# IDEFICS3_ROCO

![Stage](https://img.shields.io/badge/stage-early%20development-yellow)![License](https://img.shields.io/badge/license-Apache%202.0-blue)![Contributors Welcome](https://img.shields.io/badge/contributors-welcome-brightgreen)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb)

## Star the project

**If you appreciate my work, please consider giving it a like! 🤩**  
**I'm also looking for donations of free GPU time to complete the fine-tuning process.**  
**Please contact me if you can help! 🙏**  

## A Fine-tuned Radiology-focused Model based on Hugging Face's Idefics3 Model

This repository contains a fine-tuned version of the Hugging Face [Idefics3-8B-Llama3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) model, built on top of the Meta Llama 3.1 8B architecture. Our model, `IDEFICS3_ROCO`, has been fine-tuned on the [Radiology Objects in Context (ROCO)](https://huggingface.co/datasets/eltorio/ROCO-radiology) dataset, a large-scale medical and multimodal imaging collection.

## TL;DR

For immediate use, you can load the model directly from Hugging Face:  

```python
from transformers import AutoProcessor, Idefics3ForConditionalGeneration, image_utils
import torch
device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu') # on CPU it requires ≈ 3h/query 🙈
processor = AutoProcessor.from_pretrained(v)
model = Idefics3ForConditionalGeneration.from_pretrained(
        v, torch_dtype=torch.bfloat16
    ).to(device)

model.load_adapter("eltorio/IDEFICS3_ROCO")
```

### Model Information

* **Base Model:** Idefics3-8B-Llama3
* **Fine-tuning Dataset:** Radiology Objects in Context (ROCO)
* **License:** Apache-2.0
* **Current Status:** Fine-tuning process is finished. Contributions to complete the fine-tuning / vallidation / test processes are welcome!

### Training Progress Status

* Current checkpoint: 12267 (100% completed)
* Estimated remaining GPU time: 0 hours
* Hardware requirements: T4 GPU with >16GB VRAM
* Last update: november, 12th 2024

### Fine-tuning Code

The fine-tuning code is available as a Jupyter Notebook in the [ROCO-radiology dataset repository](https://huggingface.co/datasets/eltorio/ROCO-radiology) on Hugging Face:

* [ROCO-idefics3.ipynb](https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb)

The [Junyper Notebook](https://colab.research.google.com/#fileId=https%3A//huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb) contains the code to fine-tune the Idefics3-8B-Llama3 model on the ROCO dataset. The fine-tuning process is currently halted at checkpoint 640 (out of 24,000) due to limitations with Colab Free T4 GPU unit. Contributions to complete the fine-tuning process are welcome!

### Contributions Welcome

If you have the resources to complete the fine-tuning process, we would appreciate your contribution. Please fork this repository, finish the fine-tuning process, and submit a pull request with your updates.

### Citation

If you use this model in your work, please cite the original Idefics3 model and our fine-tuned model:

* [Idefics3-8B-Llama3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3)
* [IDEFICS3_ROCO](https://huggingface.co/eltorio/IDEFICS3_ROCO)

### Contribution Guide

1. **Technical Requirements**
   * Access to powerful GPU (T4, V100, A100 or equivalent)
   * Python environment with PyTorch
   * Disk space: ~100GB

2. **Getting Started**
   * Fork the repository
   * Resume from checkpoint 12267
   * Follow instructions in [ROCO-idefics3.ipynb](https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb)

3. **Contact**
   * For questions: [link to issues/discussions](https://huggingface.co/eltorio/IDEFICS3_ROCO/discussions)

### Docker Image

A AI training docker image is available for this model. The image and includes all necessary dependencies to run the fine-tuning process.  
You need to set the `HF_TOKEN` environment variable to your Hugging Face API token.  
You also need to have NVidia Docker container runtime installed.
Finnaly, you need to run the container with GPU support with `--gpus all` option.
The image is available on Docker Hub:  

```bash
export HF_TOKEN=hf_some_token
docker run --gpus all --user=42420:42420 -e HF_TOKEN=$HF_TOKEN -it sctg/roco-idefics3:latest bash -i  /start.sh $HF_TOKEN
```

The Dockerfile is available in the [IDEFICS_ROCO repository](https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/Dockerfile).

### Use this model

According to the Apache license you should cite this model with:  

```bibtex
@misc {ronan_l.m._2024,
	author       = { {Ronan L.M.} },
	title        = { IDEFICS3_ROCO (Revision b02598a) },
	year         = 2024,
	url          = { https://huggingface.co/eltorio/IDEFICS3_ROCO },
	doi          = { 10.57967/hf/3504 },
	publisher    = { Hugging Face }
}
```

### Acknowledgments

This work was made possible by the [Hugging Face Transformers](https://huggingface.co/) library and the [ROCO-radiology dataset](https://huggingface.co/datasets/eltorio/ROCO-radiology).