kristiannordby/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

Model Details

Model Description

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]

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

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

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

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

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]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]