TableLlama / README.md
tianshuzhang's picture
Update README.md
b4bd8ba
metadata
license: cc-by-4.0
language:
  - en
datasets:
  - osunlp/TableInstruct

TableLlama: Towards Open Large Generalist Models for Tables

Project Page: https://osu-nlp-group.github.io/TableLlama/

Paper: https://arxiv.org/abs/2311.09206

Dataset: https://huggingface.co/datasets/osunlp/TableInstruct/

Code: https://osu-nlp-group.github.io/TableLlama/

Introduction

We introduce TableLlama, an open-source large generalist model specifically tailored for various table-based tasks. The TableLlama model is trained on 🤗 TableInstruct Dataset, a meticulously curated instruction tuning dataset for tables. TableLlama is tuned on 2.6 million table-based task data, and can handle up to 8K context!

Model

TableLlama-7B

Data

The models are trained on the 🤗 TableInstruct Dataset, which includes a comprehensive table-based instruction tuning dataset that covers a variety of real-world tables and realistic tasks. We include 14 datasets of 11 tasks in total. Check out the dataset card for more details.

Training Procedure

The models are fine-tuned with the TableInstruct dataset using LongLoRA (7B), fully fine-tuning version as the base model, which replaces the vanilla attention mechanism of the original Llama-2 (7B) with shift short attention. The training takes 9 days on a 48 80*A100 cluster. Check out our paper for more details.

Evaluation

The models are evaluated on 8 in-domain datasets of 8 tasks and 6 out-of-domain datasets of 4 tasks.

Usage

You can use the models through Huggingface's Transformers library. Check our Github repo for more advanced use: https://osu-nlp-group.github.io/TableLlama/

Prompt Format

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that
appropriately completes the request.

### Instruction:
{instruction}

### Input:
{input}

### Question:
{question}

### Response:

Limitations

We've tried our best to build table generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the table tasks and datasets. Still not all table-based tasks can be covered comprehensively.

Citation

If you use the models, data, or code from this project, please cite the original paper:

@misc{zhang2023tablellama,
  title={TableLlama: Towards Open Large Generalist Models for Tables}, 
  author={Tianshu Zhang and Xiang Yue and Yifei Li and Huan Sun},
  year={2023},
  eprint={2311.09206},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}