Update README.md

README.md

@@ -1,114 +1,172 @@
 ---
-library_name: transformers
-tags:
-- research
-- lora
-- nl2sql
-- sql
 license: mit
 datasets:
 - b-mc2/sql-create-context
 language:
 - en
+metrics:
+- accuracy
+- code_eval
+library_name: transformers
 pipeline_tag: text-generation
+tags:
+- peft
+- nl2sql
+widget:
+- text: "### Task\nGenerate a SQL query to answer the following question:\n`How many heads of the departments are older than 56?`\n\n### Database Schema\nThe query will run on a database with the following schema:\nCREATE TABLE head (age INTEGER)\n\n### Answer\nGiven the database schema, here is the SQL query that answers `How many heads of the departments are older than 56?`:\n```sql"
+  example_title: "One Table"
+- text: "### Task\nGenerate a SQL query to answer the following question:\n`How many departments are led by heads who are not mentioned?`\n\n### Database Schema\nThe query will run on a database with the following schema:\nCREATE TABLE management (department_id VARCHAR);\nCREATE TABLE department (department_id VARCHAR)\n\n### Answer\nGiven the database schema, here is the SQL query that answers `How many departments are led by heads who are not mentioned?`:\n```sql"
+  example_title: "Two Tables" 
 ---
 
+# Thanks for being patient! 💜💜
+
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
-phi2-nl2sql is a finetuned model of phi-2. The dataset used is `b-mc2/sql-create-context`. This is a base model for the upcoming `gguf` version.
 
+A fine-tuned version of Phi-2 for the NL2SQL usecase on `b-mc2/sql-create-context` dataset. __*This contains just the adapters!! You need to load the Phi2 model and add these adapters*__
 
 ## Model Details
 
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
+This model has been finetuned with `b-mc2/sql-create-context` on `microsoft/phi-2`. This performed better than `defog/sqlcoder-7b-2` in terms of inference time and accuracy on the holdback dataset. The evaluation is done on `.gguf` models on CPU machine with limited RAM. The average inference times of the Phi-2, and SQLCoder are 24 secs, and 41 secs respectively. That is 41% faster on average. This is due to its smaller size. The Finetuned Phi-2 is 29% better than the SQLCoder based on execution success. The major drawback is its context window of 2048 tokens which requires additional input engineering to get results.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** Pavan Kumar Balijepalli
-- **Funded by [optional]:** Pavan Kumar Balijepalli
-- **Shared by [optional]:** Pavan Kumar Balijepalli
-- **Model type:** Casual_LM
+- **Developed by:** pavankumarbalijepalli
+- **Model type:** CASUAL_LM
 - **Language(s) (NLP):** English, SQL
 - **License:** MIT
-- **Finetuned from model [optional]:** microsoft/phi-2
+- **Finetuned from model:** [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
 
-### Model Sources [optional]
+### Model Sources
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [pavankumarbalijepalli/pr-phi2-vs-defog](https://github.com/pavankumarbalijepalli/pr-phi2-vs-defog/)
+- **Paper :** [BITS Project Paper](https://github.com/pavankumarbalijepalli/pr-phi2-vs-defog/blob/main/2021SC04115%20-%20Final.pdf)
 
 ## 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. -->
 
+Model is supposed to be used for the cases where you have a natural language question, database schema which is relevant the question to retrieve a SQL query which answers the question. The context should be below 2048 tokens. The output will be generated in postgresql.
+
 ### Direct Use
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-[More Information Needed]
+```python
+# SAME TEMPLATE AS DEFOG MODEL
+prompt = f"""### Task
+Generate a SQL query to answer the following question:
+`{data_point['question']}`
+
+### Database Schema
+The query will run on a database with the following schema:
+{data_point['context']}
+
+### Answer
+Given the database schema, here is the SQL query that answers `{data_point['question']}`:
+```sql"""
+```
+
+```python
+# USING ON CPU MACHINE
+from llama_cpp import Llama
 
-### Downstream Use [optional]
+phi2 = Llama(model_path=f"{path_to_model}/phi2_sqlcoder_f16.gguf")
+
+response = phi2(prompt=prompt, max_tokens = 200, temperature = 0.2, stop = ['```'])
+
+print(response['choices'][0]['text'].strip())
+```
+
+### Downstream Use
 
 <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
-[More Information Needed]
+```python
+# USING ON GPU MACHINE
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+# from peft import PeftModel, PeftConfig
 
-### Out-of-Scope Use
+model_name = "pavankumarbalijepalli/phi2-sqlcoder"
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    device_map="auto"
+)
 
-[More Information Needed]
+prompt = ""
 
-## Bias, Risks, and Limitations
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
+inputs.to('cuda')
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+outputs = model.generate(**inputs, max_length=1000)
+text = tokenizer.batch_decode(outputs,skip_special_tokens=True)[0]
+print(text)
+```
 
-[More Information Needed]
+### Out-of-Scope Use
 
-### Recommendations
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+__Generating Unintended Code:__
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+While the model can translate natural language into SQL queries, it may not be robust enough to handle complex logic or edge cases. Using it to generate critical production code could lead to errors or unexpected behavior in databases.
 
-## How to Get Started with the Model
+__Security Risks:__
 
-Use the code below to get started with the model.
+NL2SQL models can be susceptible to adversarial attacks where malicious users input natural language designed to trick the model into generating SQL code with security vulnerabilities, like SQL injection attacks.
 
-[More Information Needed]
+__Beyond its Training Scope:__
 
-## Training Details
+The model is trained on a specific SQL Language (e.g., PostgreSQL). Using it for a different SQL Syntax (e.g., MS SQL Server) could lead to inaccurate or nonsensical SQL queries.
 
-### Training Data
+## Bias, Risks, and Limitations
 
-<!-- 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. -->
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-[More Information Needed]
+__Bias and Fairness:__
 
-### Training Procedure 
+The model's training data may contain biases that are reflected in the generated SQL queries. This could lead to unfair or discriminatory outcomes, especially if the data is not carefully curated.
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+__Interpretability and Explainability:__
 
-#### Preprocessing [optional]
+NL2SQL models are often "black boxes" where it's difficult to understand how they translate natural language to SQL. This lack of interpretability makes it challenging to debug errors or ensure the generated queries are safe and efficient.
 
-[More Information Needed]
+__Replacing Human Expertise:__
 
+While the model can automate some SQL query generation tasks, it shouldn't be a complete replacement for human database administrators or analysts. Understanding the data schema and database design is crucial for writing efficient and secure SQL queries.
 
-#### 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 -->
+### Recommendations
 
-#### Speeds, Sizes, Times [optional]
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
 
-[More Information Needed]
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+```
+@misc{b-mc2_2023_sql-create-context,
+  title   = {sql-create-context Dataset},
+  author  = {b-mc2}, 
+  year    = {2023},
+  url     = {https://huggingface.co/datasets/b-mc2/sql-create-context},
+  note    = {This dataset was created by modifying data from the following sources: \cite{zhongSeq2SQL2017, yu2018spider}.},
+}
+```
 
 ## Evaluation
 
@@ -120,33 +178,50 @@ Use the code below to get started with the model.
 
 <!-- This should link to a Dataset Card if possible. -->
 
-[More Information Needed]
+Used b-mc2/sql-create-context and split the data into training and testing datasets. The holdout dataset is used for testing the model. 
 
 #### Factors
 
 <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+The complexity of the questions are calculated using the number of tables per question, number of joins, group by, and sub queries per answer. This complexity is used to prepare the test data by stratifying the split around the complexity.
 
-[More Information Needed]
 
 #### Metrics
 
 <!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
+* __Execution Success:__ This metric is used to find out if the generated query is executable without arising any errors. For this, a sqllite3 connection is made to the memory, and using context the dummy tables are created. Then the predicted SQL is executed. This checks out if the generated query is in proper syntax, and if the model is hallucinating any new columns.
+* __Inference Time:__ This metric is used to find out which model is providing results in less amount of time. This combined with the execution success, gives the efficiency of the model.
+- 
 ### Results
 
-[More Information Needed]
+* __Execution Success:__ Finetuned Phi-2 has 29% more success rate than the SQLCoder-7b-2
+* __Inference Time:__ Finetuned Phi-2 has 41% increased inference speed than SQLCoder-7b-2  
 
 #### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+* __Reduced Inference Time and Memory Footprint:__ The fine-tuned Phi-2 model
+demonstrated a reduction in inference time and memory usage compared to the DeFog
+SQLCoder. This is attributed to Phi-2's smaller size and the efficiency of quantization
+techniques employed during fine-tuning. This finding implies that NL2SQL models can
+be deployed on lower-powered devices like laptops or even mobile phones, potentially
+democratizing access to this technology for a wider range of users.
+
+* __Competitive Performance on Easy and Medium Queries:__ The fine-tuned Phi-2
+achieved comparable performance to the DeFog SQLCoder in terms of accuracy on easy,
+medium, and hard difficulty queries. This indicates that Phi-2, despite its smaller size,
+can effectively handle a significant portion of real-world NL2SQL tasks, especially for
+simpler queries.
+
+* __Challenges with Complex Queries:__ While Phi-2 performed well on easier queries, it
+encountered challenges with complex queries, exhibiting a drop in execution success
+compared to the DeFog SQLCoder. This highlights the trade-off between model size and
+complexity, suggesting that larger models might still be necessary for tackling highly
+intricate tasks.
+
+* __Potential for Further Improvement:__ The fine-tuning process employed in this study
+can be further optimized by exploring different hyperparameter configurations and
+potentially investigating alternative fine-tuning techniques like adapter-based methods.
+This optimization has the potential to improve the model's performance on complex
+queries while maintaining its efficiency.
 
 ## Environmental Impact
 
@@ -154,56 +229,14 @@ Use the code below to get started with the model.
 
 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).
 
-- **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]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
+- **Hardware Type:** A100 PCIE 40GB X1
+- **Hours used:** 18 Hours
+- **Cloud Provider:** Google Cloud
+- **Compute Region:** Asia-East-1
+- **Carbon Emitted:** 2.52 kg eq. CO2
 
-#### Hardware
 
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## 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. -->
 
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]