---
license: cc-by-nc-4.0
language:
- en
---
# Jellyfish-13B
<!-- Provide a quick summary of what the model is/does. -->
<img src="https://i.imgur.com/d8Bl04i.png" alt="PicToModel" width="330"/>

## Model Details
Jellyfish-13B is a large language model with 13 billion parameters, designed specifically for data managment and preprocessing tasks, such as entity matching, data imputation, error detection, and schema matching.

We fine-tuned [Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B) using the datasets related to data preprocessing tasks.
Its performance is competitive, standing up well against prior state-of-the-art algorithms and LLMs such as OpenAI GPT 3.5 and GPT 4 ([evaluated by our previous work](https://arxiv.org/abs/2308.16361)).
Note that Jellyfish is only a 13B model and can be run locally for low cost and data security.

|  Task  | Dataset | Non-LLM SoTA<sup>1</sup> | GPT-3.5<sup>2</sup> | GPT-4<sup>2</sup> | Jellyfish-13B| Jellyfish-13B-Resoning |
| ---- | ---- | ---- | ---- | ---- | ---- | ---- |
| Entity Matching  | Fodors-Zagats  | 100  | 100 | 100 | 100 | 100 |
| Entity Matching  | Beer           | 94.37| 96.30 | 100 | 93.33 | 100 | 
| Entity Matching  | iTunes-Amazon  | 97.06| 96.43 | 100 | 96.30 | 96.15 | 
| Entity Matching  | Walmart-Amazon | 86.76| 86.17 | 90.27 | 80.71 | 85.16 | 
| Entity Matching  | DBLP-ACM       | 98.99| 96.99 | 97.44 | 97.35 | 95.74 | 
| Entity Matching  | DBLP-GoogleScholar | 95.60| 76.12 | 91.87 | 92.83 | 89.45 | 
| Entity Matching  | Amazon-Google  | 75.58| 66.53 | 74.21 | 72.69 | 56.64 | 
| Data Imputation  |  Restaurant    | 77.20| 94.19 | 97.67 | 94.19 | 93.02 | 
| Data Imputation  |  Buy           | 96.50| 98.46 | 100 | 100 | 100 | 
| Error Detection  |  Hosptial      | 99.10| 90.74 | 90.74 | 92.21 | 65.66 | 
| Error Detection  |  Adult         | 94.40| 92.01 | 92.01 | 96.62 | 90.13 | 
| Schema Matching  |  Sythea        | 38.50| 57.14 | 66.67 | 36.36 | 30.77 |  

_Accuracy as the metric for data imputation, and the F1 score for other tasks._  
_For GPT-3.5, GPT-4 we used the few-shot approach, while for Jellyfish and Jellyfish-Reasoning, the zero-shot approach was employed._
1.  
  [Ditto](https://arxiv.org/abs/2004.00584) for Entity Matching  
  [SMAT](https://www.researchgate.net/publication/353920530_SMAT_An_Attention-Based_Deep_Learning_Solution_to_the_Automation_of_Schema_Matching) for Schema Matching  
  [HoloDetect](https://arxiv.org/abs/1904.02285) for Error Detection  
  [HoloClean](https://arxiv.org/abs/1702.00820) for Data Imputation  
2.  
  [Large Language Models as Data Preprocessors](https://arxiv.org/abs/2308.16361)
  

We release two versions of Jellyfish: the Jellyfish-13B (the main branch) and Jellyfish-13B-Reasoning.
As the names suggest, Jellyfish-13B focuses on providing accurate, direct answers. 
In contrast, Jellyfish-13B-Reasoning distills knowledge from GPT-4. It fine-tuned with data containing reasons and chain-of-thought responses for solving data preprocessing tasks 
generated by GPT-4.

The two versions are designed for different application scenarios.
Jellyfish-13B is suitable for integration into larger data management systems due to its simple and clear responses that can be easily transformed into code.
On the other hand, Jellyfish-13B-Reasoning is more user-oriented, with responses that offer deeper insights into the data.

**Jellyfish paper will be coming soon!**

- **Developed by:** Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada
- **Contact: dongyuyang@nec.com**
- **Funded by:** NEC Corporation, Osaka University
- **Language(s) (NLP):** English
- **License:** Non-Commercial Creative Commons license (CC BY-NC-4.0)
- **Finetuned from model:** [Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B)

## Prompt Template
```
### Instruction:

<prompt> (without the <>)

### Response:
```

## Training Details

### Training Data
We utilized the training and validation sets from the paper [Can Foundation Models Wrangle Your Data?](https://arxiv.org/abs/2205.09911) to fine-tune Jellyfish
The original datasets is [HazyResearch/fm_data_tasks](https://github.com/HazyResearch/fm_data_tasks).
We revised this data and constructed an instruction tuning dataset suitable for fine-tuning LLM, mirroring the style of [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).

### Training Method

We used LoRA to speed up the training process, targeting the q_proj and v_proj modules.

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
Here are the prompts we used for both fine-tuning the model and for inference. Feel free to explore different prompts on your own to achieve the best generation quality.

### JellyFish-13B
#### For Entity Matching
```
You are tasked with determining whether two records listed below are the same based on the information provided.
Carefully compare the {attribute 1}, {attribute 2}... for each record before making your decision.  
Note: Missing values (N/A or \"nan\") should not be used as a basis for your decision.  
Record A: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]
Record B: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]  
Are record A and record B the same entity? Choose your answer from: [Yes, No]
```
#### For Data Imputation
```
You are presented with a {keyword} record that is missing a specific attribute: {attribute X}.
Your task is to deduce or infer the value of {attribute X} using the available information in the record.  
You may be provided with fields like {attribute 1}, {attribute 2}, ... to help you in the inference.  
Record: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}, ...]  
Based on the provided record, what would you infer is the value for the missing attribute {attribute X}?  
Answer only the value of {attribute X}.
```
#### For Error Detection
_There are two forms of the error detection task.  
In the first form, a complete record row is provided, and the task is to determine if a specific value is erroneous.  
In the second form, only the value of a specific attribute is given, and the decision about its correctness is based solely on the attribute's name and value.  
The subsequent prompt examples pertain to these two forms, respectively._
```
Your task is to determine if there is an error in the value of a specific attribute within the whole record provided.
The attributes may include {attribute 1}, {attribute 2}, ...
Errors may include, but are not limited to, spelling errors, inconsistencies, or values that don't make sense given the context of the whole record.
Record [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]
Attribute for Verification: [{attribute X}: {attribute X value}]
Question: Is there an error in the value of {attribute X}? Choose your answer from: [Yes, No]
```
```
Your task is to determine if there is an error in the value of a specific attribute.
The attributes may belong to a healthcare-related record and could be one of the following: {attribute 1}, {attribute 2}, ...
Errors can include, but are not limited to, spelling errors, inconsistencies, or values that don't make sense for that attribute.  
Note: Missing values (N/A or \"nan\") are not considered errors.
Attribute for Verification: [{attribute X}: {attribute X value}]
Question: Is there an error in the value of {attribute X}? Choose your answer from: [Yes, No]
```
#### For Schema Matching
```
Your task is to determine if the two attributes (columns) are semantically equivalent in the context of merging two tables.
Each attribute will be provided by its name and a brief description.
Your goal is to assess if they refer to the same information based on these names and descriptions provided.
Attribute A is [name: {the value of name}, description: {the value of description}].
Attribute B is [name: {the value of name}, description: {the value of description}].
Are Attribute A and Attribute B semantically equivalent? Choose your answer from: [Yes, No]
```

### For JellyFish-13B-reasoning
#### For Entity Matching
```
You are tasked with determining whether two products listed below are the same based on the information provided.
Carefully examine all the attributes before making your decision.  
Note: Missing values (N/A or \"nan\") should not be used as a basis for your decision.  
Record A: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]  
Record B: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]  
Are record A and record B the same entity?  
After your reasoning, finish your response in a separate line with and ONLY with your final answer. Choose your final answer from [Yes, No].  
```
#### For Data Imputation

#### For Error Detection

#### For Schema Matching


<!--
## Bias, Risks, and Limitations

 This section is meant to convey both technical and sociotechnical limitations. 
As of now, we've tested Jellyfish exclusively with the test sets from the benchmark datasets mentioned earlier. 

We're in the process of assessing its performance on additional datasets.
-->

<!--## Citation


 If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section.

```bibtex
@article{
  title = {Can Foundation Models Wrangle Your Data?},
  author = {Avanika Narayan, Ines Chami, Laurel Orr, Simran Arora, Christopher Ré},
  booktitle = {arXiv:2205.09911},
  year = {2022}  
}

@software{hunterlee2023orcaplaty1
  title = {OpenOrcaPlatypus: Llama2-13B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset and Merged with divergent STEM and Logic Dataset Model},
  author = {Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz and Bleys Goodson and Wing Lian and Guan Wang and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
  year = {2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},
  howpublished = {\url{https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B},
}
@article{platypus2023,
    title={Platypus: Quick, Cheap, and Powerful Refinement of LLMs}, 
    author={Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz},
    booktitle={arXiv preprint arxiv:2308.07317},
    year={2023}
}
@software{OpenOrcaxOpenChatPreview2,
  title = {OpenOrcaxOpenChatPreview2: Llama2-13B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset},
  author = {Guan Wang and Bleys Goodson and Wing Lian and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
  year = {2023},
  publisher = {HuggingFace},
  journal = {HuggingFace repository},
  howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B},
}
@software{openchat,
  title = {{OpenChat: Advancing Open-source Language Models with Imperfect Data}},
  author = {Wang, Guan and Cheng, Sijie and Yu, Qiying and Liu, Changling},
  doi = {10.5281/zenodo.8105775},
  url = {https://github.com/imoneoi/openchat},
  version = {pre-release},
  year = {2023},
  month = {7},
}
@misc{mukherjee2023orca,
      title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, 
      author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
      year={2023},
      eprint={2306.02707},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{touvron2023llama,
    title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, 
    author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
    year={2023},
    eprint= arXiv 2307.09288
}
@misc{longpre2023flan,
      title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning}, 
      author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts},
      year={2023},
      eprint={2301.13688},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}
@article{hu2021lora,
  title={LoRA: Low-Rank Adaptation of Large Language Models},
  author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu},
  journal={CoRR},
  year={2021}
}
-->


<!--**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]-->