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 Details

Model Description

• Developed by: Merwin
• Model type: PEFT adapter (LoRA) for Causal Language Modeling
• Language(s): English
• License: Apache 2.0
• Fine-tuned from model: unsloth/llama-3.2-3b-unsloth-bnb-4bit

Model Sources

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

How to Get Started with the Model

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained(
    "unsloth/llama-3.2-3b-unsloth-bnb-4bit",
    device_map="auto",
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3.2-3b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "mervp/SQLGenie")

prompt = "List the customers from Canada."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

#
OR
#
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="mervp/SQLGenie",
    max_seq_length=2048,
    dtype=None,                         
    # load_in_4bit=True,
)