yuyangdong commited on
Commit
6fdce9f
·
1 Parent(s): cb1bfd0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -7
README.md CHANGED
@@ -4,22 +4,25 @@ license: cc-by-nc-4.0
4
  language:
5
  - en
6
  ---
7
- # Jellyfish-0-13B
8
  <!-- Provide a quick summary of what the model is/does. -->
9
  <img src="https://i.imgur.com/d8Bl04i.png" alt="PicToModel" width="330"/>
10
 
11
  ## Model Details
12
- Jellyfish is a model designed specifically for data preprocessing tasks, including entity matching, data imputation, error detection, and schema matching.
13
 
14
- We fine-tuned [Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B) using data derived from benchmark datasets for those data preprocessing tasks.
 
15
 
16
- Its performance is competitive, standing up well against prior state-of-the-art algorithms and larger language models like GPT 3.5 and GPT 4.
 
 
 
17
 
18
- We have released two versions of Jellyfish: the main version and a variant called "Jellyfish-reasoning."
19
-
20
- As the names suggest, the main version focuses on providing accurate, direct answers. In contrast, Jellyfish-reasoning can generate not only the final answer to data processing queries but also the reasons behind its decisions.
21
 
22
  - **Developed by:** Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada
 
23
  - **Funded by:** NEC Corporation, Osaka University
24
  - **Language(s) (NLP):** English
25
  - **License:** Non-Commercial Creative Commons license (CC BY-NC-4.0)
 
4
  language:
5
  - en
6
  ---
7
+ # Jellyfish-13B
8
  <!-- Provide a quick summary of what the model is/does. -->
9
  <img src="https://i.imgur.com/d8Bl04i.png" alt="PicToModel" width="330"/>
10
 
11
  ## Model Details
12
+ Jellyfish-13B is a 13B large language model designed specifically for data managment and preprocessing tasks, such as entity matching, data imputation, error detection, and schema matching.
13
 
14
+ We fine-tuned [Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B) using data preprocessing tasks datasets.
15
+ Its performance is competitive, standing up well against prior state-of-the-art algorithms and OpenAI GPT 3.5 and GPT 4, which is only 13B model and run locally for low cost and data security.
16
 
17
+ We have released two versions of Jellyfish: the Jellyfish-13B and Jellyfish-13B-Reasoning.
18
+ As the names suggest, Jellyfish-13B focuses on providing accurate, direct answers.
19
+ In contrast, Jellyfish-13B-Reasoning is distilled by GPT4, which is fine-tuned with data of the reasons and chain-of-thought responses for solving data preprocessing tasks
20
+ generated by OpenAI GPT-4.
21
 
22
+ Jellyfish paper will coming soon!
 
 
23
 
24
  - **Developed by:** Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada
25
+ - **Contact: [email protected]**
26
  - **Funded by:** NEC Corporation, Osaka University
27
  - **Language(s) (NLP):** English
28
  - **License:** Non-Commercial Creative Commons license (CC BY-NC-4.0)