SQLGenie - LoRA Fine-Tuned LLaMA 3B for Text-to-SQL Generation

SQLGenie is a lightweight LoRA adapter fine-tuned on top of Unsloth’s 4-bit LLaMA 3 (3B) model. It is designed to convert natural language instructions into valid SQL queries with minimal compute overhead, making it ideal for integrating into data-driven applications,or chat interfaces. it has been trained over 100K types of text based on various different domains such as Education, Technical, Health and more

Model Highlights

• Base model: Llama3 3B
• Tokenizer: Compatible with Llama3 3B
• Fine tuned for: Text to SQL Converter
• Accuracy: > 85%
• Language: English Natural Language Sentences fientuned
• Format: safetensors

Model Dependencies

• Python Version: 3.10
• libraries: unsloth
• pip install unsloth

Model Description

• Developed by: Merwin
• Model type: PEFT adapter (LoRA) for Causal Language Modeling
• Language(s): English
• Fine-tuned from model: unsloth/llama-3.2-3b-unsloth-bnb-4bit

Model Sources

• Repository: https://huggingface.co/mervp/SQLGenie

Uses

Direct Use

This model can be directly used to generate SQL queries from natural language prompts. Example use cases include:

• Building AI assistants for databases
• Enhancing Query tools with NL-to-SQL capabilities
• Automating analytics queries in various domains

Bias, Risks, and Limitations

While the model has been fine-tuned for SQL generation, it may:

• Produce invalid SQL for a very few edge cases
• Infer incorrect table or column names not present in prompt
• Assume a generic SQL dialect (closer to MySQL/PostgreSQL Databases)

Recommendations

• Always validate and test generated queries before execution in a production database.

Thanks for visiting and downloading this model! If this model helped you, please consider leaving a 👍 like. Your support helps this model reach more developers and encourages further improvements if any.

How to Get Started with the Model

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="mervp/SQLGenie",
    max_seq_length=2048,
    dtype=None,
)

prompt = """ You are an text to SQL query translator.
             Users will ask you questions in English
             and you will generate a SQL query based on their question
             SQL has to be simple, The schema context has been provided to you.


### User Question:
{}

### Sql Context:
{}

### Sql Query:
{}
"""

question = "List the names of customers who have an account balance greater than 6000."
schema = """
CREATE TABLE socially_responsible_lending (
    customer_id INT,
    name VARCHAR(50),
    account_balance DECIMAL(10, 2)
);

INSERT INTO socially_responsible_lending VALUES
    (1, 'james Chad', 5000),
    (2, 'Jane Rajesh', 7000),
    (3, 'Alia Kapoor', 6000),
    (4, 'Fatima Patil', 8000);
"""

inputs = tokenizer(
    [prompt.format(question, schema, "")],
    return_tensors="pt",
    padding=True,
    truncation=True
).to("cuda")

output = model.generate(
    **inputs,
    max_new_tokens=256, 
    temperature=0.2,  
    top_p=0.9,          
    top_k=50,        
    do_sample=True     
)

decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)

if "### Sql Query:" in decoded_output:
    sql_query = decoded_output.split("### Sql Query:")[-1].strip()
else:
    sql_query = decoded_output.strip()

print(sql_query)