qwen35-08b-text2sql

Tuana/qwen35-08b-text2sql is a demo Text-to-SQL model fine-tuned from Qwen/Qwen3.5-0.8B.

It was fine-tuned on a small, specific synthetic SQL dataset for demonstration purposes. It is not intended to be a general Text-to-SQL model for arbitrary schemas or production databases.

Model Details

• Base model: Qwen/Qwen3.5-0.8B
• Task demo: Text-to-SQL style SQL generation
• Fine-tuning method: LoRA SFT, merged into a full checkpoint
• Training platform: Google Cloud Vertex AI
• Training container: Hugging Face PyTorch Training Deep Learning Container
• Dataset: Tuana/synthetic-sql-dataset
• Model format: Merged transformers checkpoint

What This Model Demonstrates

This model demonstrates a small fine-tuning workflow:

1. Generate a synthetic SQL instruction dataset
2. Fine-tune a small Qwen base model on Vertex AI
3. Merge the LoRA adapter into the base checkpoint
4. Serve or compare the result in a small demo app

The demo dataset uses a small synthetic database domain with tables such as:

• department
• management
• head

The model should be viewed as a demo artifact for this specific setup, not as a robust SQL assistant.

Example Prompt Format

Given this database schema:
CREATE TABLE department (
  department_id VARCHAR,
  name VARCHAR,
  creation VARCHAR
);
CREATE TABLE management (
  department_id VARCHAR,
  head_id VARCHAR,
  temporary_acting VARCHAR
);
CREATE TABLE head (
  head_id VARCHAR,
  name VARCHAR,
  born_state VARCHAR
);

Write a SQL query for:
List all department names.

SQL: