mrcmilo/phi3-text2sql-lora

Phi-3-SQL-Expert (GGUF)

This is a specialized Text-to-SQL model fine-tuned from the Microsoft Phi-3-mini-4k-instruct architecture. It has been optimized using Unsloth to provide high-accuracy SQL generation while remaining lightweight enough to run on consumer hardware.

Key Features

• Architecture: Phi-3-mini (3.8B parameters)
• Quantization: Q4_K_M GGUF (Optimized balance of speed and logic)
• Training Technique: Fine-tuned using Lora with Unsloth.
• Format: GGUF (Ready for Ollama, LM Studio, and llama.cpp)

Usage Instructions

Ollama (Recommended)

To deploy locally:

1. Download the .gguf file.
2. Create a file named Modelfile and paste the following:

FROM ./phi3-sql-expert.Q4_K_M.gguf

TEMPLATE """<|system|>
You are a helpful assistant that writes SQL queries. Given a user question and a table schema, output only the SQL code.<|end|>
<|user|>
{{ .Prompt }}<|end|>
<|assistant|>
"""

PARAMETER stop "<|end|>"
PARAMETER temperature 0.1
PARAMETER num_ctx 2048

3. Run ollama create sql-expert -f Modelfile

4. Run ollama run sql-expert

Evaluation Data

The model was fine-tuned on the sql-create-context dataset, focusing on:

Mapping natural language to complex SELECT, WHERE, and JOIN statements.

Understanding table schemas provided in the prompt.

Maintaining strict SQL syntax.

Recommended Settings

Temperature: 0.0 or 0.1 (SQL requires deterministic output).

Stop Tokens: Ensure <|end|> is set as a stop sequence to prevent "infinite looping" generation.

Context Window: 2048 or 4096 tokens.

Model Developer: mrcmilo

Base Model: Phi-3-mini-4k-instruct