README.md

---
license: cc-by-nc-4.0
language:
- en
---
# Jellyfish-8B
<!-- Provide a quick summary of what the model is/does. -->
<!--
<img src="https://i.imgur.com/d8Bl04i.png" alt="PicToModel" width="330"/>
-->
<img src="https://i.imgur.com/E1vqCIw.png" alt="PicToModel" width="330"/>


## Model Details
Jellyfish-8B is a large language model equipped with 8 billion parameters.   
We fine-tuned the [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) model using the datasets pertinent to data preprocessing tasks.
The training data include two parts:
* Jellyfish-13B training data
* GPT4 generated reasoning data for data preprocessing tasks.

<!-- Jellyfish-7B vs GPT-3.5-turbo wining rate by GPT4 evaluation is 56.36%. -->

More details about the model can be found in the [Jellyfish paper](https://arxiv.org/abs/2312.01678).

- **Developed by:** Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada  
- **Contact: [email protected]**  
- **Funded by:** NEC Corporation, Osaka University  
- **Language(s) (NLP):** English  
- **License:** Non-Commercial Creative Commons license (CC BY-NC-4.0)  
- **Finetuned from model:** [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) 
## Citation

If you find our work useful, please give us credit by citing:

```
@article{zhang2023jellyfish,
  title={Jellyfish: A Large Language Model for Data Preprocessing},
  author={Zhang, Haochen and Dong, Yuyang and Xiao, Chuan and Oyamada, Masafumi},
  journal={arXiv preprint arXiv:2312.01678},
  year={2023}
}
```

## Performance on seen tasks

|  Task  | Type | Dataset | Non-LLM SoTA<sup>1</sup> | GPT-3.5<sup>2</sup> | GPT-4<sup>2</sup> | Jellyfish-13B| Jellyfish-7B |  Jellyfish-8B | 
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |  ---- |  
| Entity Matching  | Seen | Fodors-Zagats  | 100  | 100 | 100 | 100 | 100 | 92.68 |
| Entity Matching  | Seen | Beer           | 94.37| 96.30 | 100 | 96.77 | 96.55| 96.30 |
| Entity Matching  | Seen | iTunes-Amazon  | 97.06| 96.43 | 100 | 98.11 | 96.30| 92.00 |
| Entity Matching  | Seen | DBLP-ACM       | 98.99| 96.99 | 97.44 | 98.98 | 98.88| 98.76 |
| Entity Matching  | Seen | DBLP-GoogleScholar | 95.60| 76.12 | 91.87 | 98.51 | 95.15| 93.20 | 
| Entity Matching  | Seen | Amazon-Google  | 75.58| 66.53 | 74.21 | 81.34 | 80.83 |  74.49 |
| Entity Matching  | Unseen | Walmart-Amazon | 86.76| 86.17 | 90.27 | 89.42 | 85.64 | 89.97 |
| Entity Matching  | Unseen | Abt-Buy | 89.33 | -- | 92.77 | 89.58 | 82.38 |  92.54 |
| Data Imputation  | Seen |  Restaurant    | 77.20| 94.19 | 97.67 | 94.19 | 88.37 |  87.21 |
| Data Imputation  | Seen |  Buy           | 96.50| 98.46 | 100 | 100 | 96.62 |  92.31 |
| Data Imputation  | Unseen |  Filpkart    | 68.00 | -- | 89.94 | 81.68 | 79.44|  90.17 |
| Data Imputation  | Unseen |  Phone       | 86.70| -- | 90.79 | 87.21 | 85.00|  83.92 |
| Error Detection  | Seen |  Hosptial      | 94.40| 90.74 | 90.74 | 95.59 | 96.27 |  80.72|
| Error Detection  | Seen |  Adult         | 99.10| 92.01 | 92.01 | 99.33 | 91.96 |  81.72|
| Error Detection  | Unseen |  Flights     | 81.00 | -- | 83.48  | 82.52 | 66.92 | 75.18 |
| Error Detection  | Unseen |  Rayyan      | 79.00| -- | 81.95 | 90.65 | 69.82 | 91.54 |
| Schema Matching  | Seen |  Sythea        | 38.50| 57.14 | 66.67 | 36.36 | 44.44 | 27.27 |
| Schema Matching  | Seen |  MIMIC        | 20.00| -- | 40.00 | 40.00 | 40.00 | 34.04|
| Schema Matching  | Unseen |  CMS        | 50.00| -- | 19.35 | 59.29 | 13.79 |  56.72|

_For GPT-3.5 and GPT-4, we used the few-shot approach on all datasets. However, for Jellyfish-13B and Jellyfish-Interpreter, the few-shot approach is disabled on seen datasets and enabled on unseen datasets._   
_Accuracy as the metric for data imputation and the F1 score for other tasks._ 

## Performance on unseen tasks

### Column Type Annotation

| Dataset | RoBERTa (159 shots)<sup>1</sup> | GPT-3.5<sup>1</sup> | GPT-4 | Jellfish-13B| Jellyfish-7B |   Jellyfish-8B |
| ---- | ---- | ---- | ---- | ---- | ----|----|
| SOTAB | 79.20 | 89.47 | 91.55 | 82.00 | 80.89 | 67.21|

_Few-shot is disabled for Jellyfish-13B._   

1. Results from [Column Type Annotation using ChatGPT](https://arxiv.org/abs/2306.00745)

### Attribute Value Extraction

| Dataset |Stable Beluga 2 70B<sup>1</sup> | SOLAR 70B<sup>1</sup> | GPT-3.5<sup>1</sup> | GPT-4 <sup>1</sup>| Jellfish-13B | Jellyfish-7B|   Jellyfish-8B |
| ---- | ---- | ---- | ---- | ---- | ---- | ----| ----|
| AE-110k | 52.10 | 49.20 | 61.30 | 55.50 | 58.12 | 76.85| 69.78|
| OA-Mine | 50.80 | 55.20 | 62.70 | 68.90 | 55.96 | 76.04| 78.83|


## Prompt Template
```
[INST]:

<prompt> (without the <>)

[\INST]]
```