Jellyfish-13B

We also build Jellyfish-7B, a light version with 7 billion parameters!
It keeps the powerfull data propcessing performance with faster inference speed and better reasoning ability!

Model Details

Jellyfish-13B is a large language model equipped with 13 billion parameters. It's tailored specifically for data preprocessing tasks, including entity matching, data imputation, error detection, and schema matching.

We fine-tuned the Open-Orca/OpenOrca-Platypus2-13B model using the datasets pertinent to data preprocessing tasks. Its performance is competitive, rivaling previous state-of-the-art algorithms and LLMs such as OpenAI's GPT 3.5 and GPT 4 (as demonstrated in our earlier studies). It is notable that, as a 13B model, Jellyfish allows for cost-effective local execution without compromising data security. Additionally, its proficiency in handling data preprocessing tasks means that Jellyfish maintains strong performance in NLP tasks as an LLM, as evidenced by the NLP benchmark scores comparison between Jellyfish and OpenOraca-Platypus2.

We release two distinct versions of Jellyfish: Jellyfish-13B (the main branch) and Jellyfish-13B-Interpreter (the alternative branch). As the names suggest, Jellyfish-13B is tailored to deliver precise, straightforward answers. In contrast, Jellyfish-13B-Interpreter, is fine-tuned with data that includes reasoning and sequential thought processes for handling data preprocessing tasks, distilling knowledge from 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-Interpreter is more user-oriented, with responses that provide them with in-depth data insights without the necessity for advanced coding skills or an intricate grasp of statistics.

More details about the model can be found in the Jellyfish paper.

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

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 SoTA¹	GPT-3.5²	GPT-4²	Jellyfish-13B-1.1³	Jellyfish-13B-Interpreter
Entity Matching	Seen	Fodors-Zagats	100	100	100	100	100
Entity Matching	Seen	Beer	94.37	96.30	100	96.77	100
Entity Matching	Seen	iTunes-Amazon	97.06	96.43	100	98.11	96.15
Entity Matching	Seen	DBLP-ACM	98.99	96.99	97.44	98.98	95.74
Entity Matching	Seen	DBLP-GoogleScholar	95.60	76.12	91.87	98.51	89.45
Entity Matching	Seen	Amazon-Google	75.58	66.53	74.21	81.34	56.64
Entity Matching	Unseen	Walmart-Amazon	86.76	86.17	90.27	89.42	85.16
Entity Matching	Unseen	Abt-Buy	89.33	--	92.77	89.58	--
Data Imputation	Seen	Restaurant	77.20	94.19	97.67	94.19	93.02
Data Imputation	Seen	Buy	96.50	98.46	100	100	100
Data Imputation	Unseen	Filpkart	68.00	--	89.94	81.68	--
Data Imputation	Unseen	Phone	86.70	--	90.79	87.21	--
Error Detection	Seen	Hosptial	94.40	90.74	90.74	95.59	65.66
Error Detection	Seen	Adult	99.10	92.01	92.01	99.33	90.13
Error Detection	Unseen	Flights	81.00	--	83.48	82.52	--
Error Detection	Unseen	Rayyan	79.00	--	81.95	90.65	--
Schema Matching	Seen	Sythea	38.50	57.14	66.67	36.36	30.77
Schema Matching	Seen	MIMIC	20.00	--	40.00	40.00	--
Schema Matching	Unseen	CMS	50.00	--	19.35	59.29	--

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.

Ditto for Entity Matching
SMAT for Schema Matching
HoloDetect for Error Detection seen datasets
RAHA for Error Detection unseen datasets
IPM for Data Imputation
Large Language Models as Data Preprocessors
We have updated the main branch with Jellyfish-13B version 1.1 .

Performance on unseen tasks

Column Type Annotation

Dataset	RoBERTa (159 shots)¹	GPT-3.5¹	GPT-4	Jellfish-13B-1.1
SOTAB	79.20	89.47	91.55	82.00

Few-shot is disabled for Jellyfish-13B.

Results from Column Type Annotation using ChatGPT

Attribute Value Extraction

Dataset	Stable Beluga 2 70B¹	SOLAR 70B¹	GPT-3.5¹	GPT-4 ¹	Jellfish-13B-1.1
AE-110k	52.10	49.20	61.30	55.50	58.12
OA-Mine	50.80	55.20	62.70	68.90	55.96

Few-shot is disabled for Jellyfish-13B.

Results from Product Attribute Value Extraction using Large Language Models

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? to fine-tune Jellyfish. The original datasets are from HazyResearch/fm_data_tasks, RAHA, SMAT, and IPM. We revised this data and constructed an instruction tuning dataset suitable for fine-tuning LLM, mirroring the style of OpenOrca dataset.

Training Method

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

Uses

For improved practical inference speed, we strongly recommend running Jellyfish using vLLM.

Python Script

We provide two simple Python code examples for inference using the Jellyfish model.

Using Transformers and Torch Modules

from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
import torch

if torch.cuda.is_available():
    device = "cuda"
else:
    device = "cpu"

# Model will be automatically downloaded from HuggingFace model hub if not cached.
# Model files will be cached in "~/.cache/huggingface/hub/models--NECOUDBFM--Jellyfish/" by default.
# You can also download the model manually and replace the model name with the path to the model files.
model = AutoModelForCausalLM.from_pretrained(
    "NECOUDBFM/Jellyfish",
    torch_dtype=torch.float16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("NECOUDBFM/Jellyfish")

system_message = "You are an AI assistant that follows instruction extremely well. Help as much as you can."

# You need to define the user_message variable based on the task and the data you want to test on.
user_message = "Hello, world."

prompt = f"{system_message}\n\n### Instruction:\n\n{user_message}\n\n### Response:\n\n"
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to(device)

# You can modify the sampling parameters according to your needs.
generation_config = GenerationConfig(
    do_samples=True,
    temperature=0.35,
    top_p=0.9,
)

with torch.no_grad():
    generation_output = model.generate(
        input_ids=input_ids,
        generation_config=generation_config,
        return_dict_in_generate=True,
        output_scores=True,
        max_new_tokens=1024,
        pad_token_id=tokenizer.eos_token_id,
        repetition_penalty=1.15,
    )

output = generation_output[0]
response = tokenizer.decode(
    output[:, input_ids.shape[-1] :][0], skip_special_tokens=True
).strip()

print(response)

Using vLLM

from vllm import LLM, SamplingParams

# To use vllm for inference, you need to download the model files either using HuggingFace model hub or manually.
# You should modify the path to the model according to your local environment.
path_to_model = (
    "/workspace/models/Jellyfish"
)

model = LLM(model=path_to_model)

# You can modify the sampling parameters according to your needs.
# Caution: The stop parameter should not be changed.
sampling_params = SamplingParams(
    temperature=0.35,
    top_p=0.9,
    max_tokens=1024,
    stop=["### Instruction:"],
)

system_message = "You are an AI assistant that follows instruction extremely well. Help as much as you can."

# You need to define the user_message variable based on the task and the data you want to test on.
user_message = "Hello, world."

prompt = f"{system_message}\n\n### Instruction:\n\n{user_message}\n\n### Response:\n\n"
outputs = model.generate(prompt, sampling_params)
response = outputs[0].outputs[0].text.strip()
print(response)

Prompts

We provide the prompts used for both the model's fine-tuning and inference. You can structure your data according to these prompts. However, we encourage experimenting with different prompts to potentially achieve optimal 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 {keyword} 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: {value of name}, description: {value of description}].
Attribute B is [name: {value of name}, description: {value of description}].
Are Attribute A and Attribute B semantically equivalent? Choose your answer from: [Yes, No].

For Column Type Annotation

We follow the prompt in Column Type Annotation using ChatGPT (text+inst+2-step).

For Attribute Value Extraction

We follow the prompt in Product Attribute Value Extraction using Large Language Models (textual, w/o examples).

JellyFish-13B-Interpreter

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

You are presented with a {keyword} record that is missing a specific attribute {attribute X}.
Your task is to deduce or infer the manufacturer of the product 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 product record, what would you infer is the value for the missing attribute {attribute X}?
After your reasoning, finish your response in a separate line with and ONLY with your final answer.
Your final answer should only consist of the value of {attribute X}.

For Error Detection

Your task is to determine if there is an error in the value of a specific attribute within the whole record provided.
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}?
After your reasoning, finish your response in a separate line with and ONLY with your final answer. Choose your final 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 {keyword} record.
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}?
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 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: {value of name}, description: {value of description}].
Attribute B is [name: {value of name}, description: {value of description}].
After your reasoning, finish your response in a separate line with and ONLY with your final answer. Choose your final answer from [Yes, No].

Sample Responses from Jellyfish-13B-Interpreter

We provide a few sample responses from Jellyfish-13B-Interpreter to demonstrate its performance.

For easier readability, we display the raw data record instead of the entire prompt.

Product A: [name: \"adobe creative suite cs3 web standard [ mac ]\", manufacturer: \"adobe\", price: \"999.0\"]
Product B: [name: \"adobe creative suite 3 ( cs3 ) web standard 3 windows upsell from dreamweaver or flash\", price: \"799.0\"]

Product A and Product B are not the same. Although both products are Adobe Creative Suite CS3 Web Standard, they are for different operating systems.
Product A is for Mac and Product B is for Windows. This difference in operating systems indicates that the products are not the same, as they are designed for different hardware and software environments.
Additionally, Product B mentions that it is an upsell from Dreamweaver or Flash, which further differentiates it from Product A.
No

Article A: [title: \"l/mrp : a buffer management strategy for interactive continuous data flows in a multimedia dbms\", authors: \"f moser , a kraiss , w klas\", venue: \"vldb\", year: \"1995\"]
Article B: [title: \"l/mrp : a buffer management strategy for interactive continuous data flows in a multimedia dbms\", authors: \"f moser , w klas\", venue: \"proceedings of the international conference on very large & hellip ; ,\", year: \"1995.0\"]

The titles of both Article A and Article B are identical, which is a strong indicator that they are the same article.
The authors of both articles are also the same, with the exception that Article B does not include the author \"a kraiss\". However, this could be due to a mistake in data entry or a missing author in Article B.
The venue for both articles is also similar, with Article A listed as \"vldb\" and Article B listed as \"proceedings of the international conference on very large & hellip ; ,\" which is likely the same conference.
The year of publication is also the same for both articles, with Article A listed as \"1995\" and Article B listed as \"1995.0\".
Given these similarities, it is reasonable to conclude that Article A and Article B are the same.
Yes

Record: [name: "le montrachet bistro", addr: "3000 paradise rd.", phone: "702-732-5651", type: "french bistro"].
missing attribute: "City"

The restaurant record provides the name, address, phone number, and type of restaurant. The name and type do not provide any specific information about the city. However, the address and phone number can be used to infer the city.
The address, "3000 paradise rd.", could potentially be in many different cities. However, the phone number, "702-732-5651", provides a clue. The area code, 702, is used in the state of Nevada, specifically in the Las Vegas metropolitan area.
Therefore, based on the area code of the phone number, it can be inferred that the restaurant is located in Las Vegas.
Las Vegas