---
license: mit
datasets:
- HuggingFaceM4/img2html
language:
- en
tags:
- code
---


**Try out the [demo](TODO:add_link)!**

# Model Description

This model converts screenshots of website components into HTML/CSS codes.

It is based on a very early checkpoint of our forthcoming vision-language foundation model, which has been fine-tuned using the [img2html](https://huggingface.co/datasets/HuggingFaceM4/img2html) dataset.

This is very much an alpha version. The goal is to kick off an effort to develop improved models capable of converting a website screenshot into actual code.

# Model Details

- **Developed by:** Hugging Face
- **Model type:** Multi-modal model (screenshot of website component to HTML/CSS code)
- **Language(s) (NLP):** en
- **License:** see [License section](#license)
- **Parent Models:** [SigLIP](https://github.com/huggingface/transformers/pull/26522) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
- **Resources for more information:**
    <!-- - [GitHub Repo](https://github.com/huggingface/m4/) -->
    - img2html dataset: [Dataset card](https://huggingface.co/datasets/HuggingFaceM4/img2html)

# License

The model is built on top of two pre-trained models: [SigLIP](https://github.com/huggingface/transformers/pull/26522) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1). As such, users should comply with the licenses of these models.

The two pre-trained models are connected to each other with newly initialized parameters that we train. These are not based on any of the two base frozen models forming the composite model. We release the additional weights we trained under an MIT license.