nnpy/qwen2-2b-instruct-table-extractor

Model Card for qwen2-7b-instruct-trl-sft-ChartQA

This model is a fine-tuned version of Qwen/Qwen2-VL-2B-Instruct. It has been trained using TRL.

Task

This model is fine-tuned for extracting tables from images with better accuracy. This model will extract tables as html table content, so it is easy to convert into any kinda table format such as csv, excel, etc

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.14.0.dev0
• Transformers: 4.49.0.dev0
• Pytorch: 2.4.1+cu121
• Datasets: 3.2.0
• Tokenizers: 0.21.0

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}