Update README.md

README.md

@@ -6,7 +6,7 @@ language:
 ---
 # Jellyfish-0-13B
 <!-- Provide a quick summary of what the model is/does. -->
-<img src="https://i.imgur.com/d8Bl04i.png" alt="PicToModel" width="350"/>
+<img src="https://i.imgur.com/d8Bl04i.png" alt="PicToModel" width="330"/>
 
 ## Model Details
 Jellyfish is a model designed specifically for data preprocessing tasks, including entity matching, data imputation, error detection, and schema matching.
@@ -17,147 +17,74 @@ Its performance is competitive, standing up well against prior state-of-the-art
 
 We have released two versions of Jellyfish: the main version and a variant called "Jellyfish-reasoning."
 
-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 a data processing problem but also the reasoning behind its decision.
-
-## Prompt Template
-```
-### Instruction:
-
-<prompt> (without the <>)
-
-### Response:
-```
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
+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.
 
 - **Developed by:** Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada
 - **Funded by:** NEC Corporation, Osaka University
-- **Model type:** [More Information Needed]
 - **Language(s) (NLP):** English
 - **License:** cc-by-4.0
 - **Finetuned from model:** [Open-Orca/OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B)
 
-## 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. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
+## Prompt Template
+```
+### Instruction:
 
-Use the code below to get started with the model.
+<prompt> (without the <>)
 
-[More Information Needed]
+### Response:
+```
 
 ## Training Details
 
 ### Training Data
+We utilized the training and validation sets of datasets for 4 data processing tasks from the paper [Can Foundation Models Wrangle Your Data?](https://arxiv.org/abs/2205.09911) to fine-tune both versions of Jellyfish.
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure 
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
+The original datasets can be accessed from their GitHub project page [HazyResearch/fm_data_tasks](https://github.com/HazyResearch/fm_data_tasks)
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+Through meticulous prompt-engineering, we constructed our datasets suitable for fine-tuning LLM, mirroring the style of [OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).
 
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
+### Training Method
 
-<!-- This should link to a Dataset Card if possible. -->
+We used LoRA to speed up the training process, targeting the q_proj and v_proj modules.
 
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
+## Uses
 
-#### Software
+<!-- 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.
 
-[hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) for fine-tuning.  
+### For JellyFish-main
+```
+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.
 
-[vLLM](https://github.com/vllm-project/vllm) for inference.
+Note: Missing values (N/A or \"nan\") should not be used as a basis for your decision.
 
-## Model Examination [optional]
+Record A: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]\nProduct B: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]
 
-<!-- Relevant interpretability work for the model goes here -->
+Are record A and record B the same entity? Choose your answer from: [Yes, No]
+```
 
-[More Information Needed]
+### For JellyFish-reasoning
+```
+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.
 
-## Environmental Impact
+Note: Missing values (N/A or \"nan\") should not be used as a basis for your decision.
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+Record A: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]\nProduct B: [{attribute 1}: {attribute 1 value}, {attribute 2}: {attribute 2 value}...]
 
-<!--Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+Are record A and record B the same entity?
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+After your reasoning, finish your response in a separate line with and ONLY with your final answer. Choose your final answer from [Yes, No].",
 
-#### Hardware
+```
 
-[More Information Needed]-->
+## 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 [optional]
+## Citation
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
@@ -168,7 +95,6 @@ Use the code below to get started with the model.
   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"},