| # ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation (ACL25 Main) |
|
|
| <a href="https://huggingface.co/datasets/xxxllz/Chart2Code-160k" target="_blank">🤗 Dataset(HuggingFace)</a> | <a href="https://modelscope.cn/datasets/Noct25/Chart2Code-160k" target="_blank">🤖 Dataset(ModelScope)</a> | <a href="https://arxiv.org/abs/2501.06598" target="_blank">📑 Paper </a> |
|
|
| This repository contains the code to train and infer ChartCoder. **Our Github repository [ChartCoder](https://github.com/thunlp/ChartCoder) updates with more details and news.** |
|
|
|
|
| ## Installation |
| 1. Clone this repo |
| ``` |
| git clone https://github.com/thunlp/ChartCoder.git |
| ``` |
| 2. Create environment |
| ``` |
| conda create -n chartcoder python=3.10 -y |
| conda activate chartcoder |
| pip install --upgrade pip # enable PEP 660 support |
| pip install -e . |
| ``` |
| 3. Additional packages required for training |
| ``` |
| pip install -e ".[train]" |
| pip install flash-attn --no-build-isolation |
| ``` |
|
|
| ## Train |
| The whole training process consists of two stages. To train the ChartCoder, ```siglip-so400m-patch14-384``` and ```deepseek-coder-6.7b-instruct``` should be downloaded first. |
|
|
| For **Pre-training**, run |
| ``` |
| bash scripts/train/pretrain_siglip.sh |
| ``` |
| For **SFT**, run |
| ``` |
| bash scripts/train/finetune_siglip_a4.sh |
| ``` |
| Please change the model path to your local path. See the corresponding ```.sh ``` file for details. |
| We also provide other training scripts, such as using CLIP ```_clip``` and multiple machines ```_m```. See ``` scripts/train ``` for further information. |
|
|
|
|
| ## Citation |
| If you find this work useful, consider giving this repository a star ⭐️ and citing 📝 our paper as follows: |
| ``` |
| @misc{zhao2025chartcoderadvancingmultimodallarge, |
| title={ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation}, |
| author={Xuanle Zhao and Xianzhen Luo and Qi Shi and Chi Chen and Shuo Wang and Wanxiang Che and Zhiyuan Liu and Maosong Sun}, |
| year={2025}, |
| eprint={2501.06598}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.AI}, |
| url={https://arxiv.org/abs/2501.06598}, |
| } |
| ``` |
