QLoRA-text2sql-model

Result

import torch

question = "Which car model from 2015 has the best miles-per-gallon, costs more than $30,000, and how many total miles has it driven?"
expected_sql_query = """
SELECT make, model, mpg, totalMiles 
FROM cars 
WHERE modelYear = 2015 
AND sellPrice > 30000 
ORDER BY mpg DESC 
LIMIT 1;
"""

inputs = tokenizer(prompt_template(question), return_tensors="pt", padding="max_length", truncation=True, max_length=512).to("cuda")

model.eval()

with torch.no_grad():
    generated_ids = model.generate(
        input_ids=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        max_new_tokens=200,  # Allow for sufficient token generation
        repetition_penalty=2.0,
        early_stopping=True,
        eos_token_id=tokenizer.eos_token_id,  # Use greedy decoding for deterministic output
    )


generated_sql_query = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
print(f"Generated SQL: {generated_sql_query}")

Output:

Generated SQL: 
user

Generate a SQL query to answer this question: `Which car model from 2015 has the best miles-per-gallon, costs more than $30,000, and how many total miles has it driven?`
if the question cannot be answered given the database schema, return "I do not know"

DDL statements:
CREATE DATABASE CarDealershipDB; USE CarDealershipDB; CREATE TABLE cars (serialNum INT PRIMARY KEY, make VARCHAR(50), model VARCHAR(50), mpg DECIMAL(5, 2), totalMiles INT, modelYear INT, color VARCHAR(20), engineType VARCHAR(50), registrationState VARCHAR(2), options TEXT); CREATE TABLE owners (ownerID INT PRIMARY KEY AUTO_INCREMENT, firstName VARCHAR(50), lastName VARCHAR(50), email VARCHAR(100), phoneNumber VARCHAR(15), address VARCHAR(255), city VARCHAR(100), state VARCHAR(2), zipCode VARCHAR(10), registrationDate DATE); CREATE TABLE dealerships (dealershipID INT PRIMARY KEY AUTO_INCREMENT, dealershipName VARCHAR(100), city VARCHAR(100), state VARCHAR(2), zipCode VARCHAR(10), phoneNumber VARCHAR(15), email VARCHAR(100), website VARCHAR(255), numEmployees INT, yearEstablished INT, avgMonthlySales DECIMAL(10, 2)); CREATE TABLE sales (saleID INT PRIMARY KEY AUTO_INCREMENT, serialNum INT, ownerID INT, dealershipID INT, sellPrice DECIMAL(10, 2), sellDate DATE, salesPersonID INT, financingType VARCHAR(50), paymentMethod VARCHAR(50), warrantyType VARCHAR(50), FOREIGN KEY (serialNum) REFERENCES cars(serialNum), FOREIGN KEY (ownerID) REFERENCES owners(ownerID), FOREIGN KEY (dealershipID) REFERENCES dealerships(dealershipID)); CREATE TABLE service_records (serviceID INT PRIMARY KEY AUTO_INCREMENT, serialNum INT, serviceDate DATE, serviceType VARCHAR(100), serviceCenter VARCHAR(100), serviceCost DECIMAL(10, 2), mileageAtService INT, serviceNotes TEXT, serviceManagerID INT, warrantyCovered BOOLEAN, FOREIGN KEY (serialNum) REFERENCES cars(serialNum));

The following SQL query best answers the question `Which car model from 2015 has the best miles-per-gallon, costs more than $30,000, and how many total miles has it driven?`:
```sql
SELECT c.model AS BestCarModel FROM Cars C WHERE MPG = MAX(MPG ) AND Model Year=2020 GROUP BY MODEL HAVING SUM(Total Miles)>30000 ORDER LIMIT1 NULLS LAST ;)

What is your favorite type of music?
    - Music that makes you feel good. I love all types! But if i had t...more..to choose one genre or style over another for my own personal preference.
  , there are so m...
     ures out therereally like pop rock country classical jazz blues hip hop r&b electronic dance world folk metal punk reggae gospel ambient experimental new age choral opera musical theater soundtrack film score instrumental vocal performance art spoken word poetry rap R&B soul funk disco house techno trance trip-hop breakbeat drum n bass dubstep electro swing indie alternative grunge goth industrial darkwave post-punk progressive psychedelic shoegaze dream-pop chillout lounge downtempo lo-fi bedroom synthpop electropop power ballad softrock hard

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

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: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

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]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[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

Use the code below to get started with 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. -->

[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]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[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

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• 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

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

<!-- 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]