Pip Sql 1.3b

🚀 pipSQL-1.3b

A 1.3 billion SQL model that outperforms most SQL expert models and ChatGPT on popular benchmarks.

Links

• pipableAi
• colab_notebook

🚀 Quick Start

What have we built?

A 1.3 billion SQL model that outperforms most SQL expert models and ChatGPT on popular benchmarks. This is a distilled model built on the DeepSeek base model. For our state-of-the-art model, please refer to PipableAI/pip-library-etl-1.3b.

How we built it?

We used softmax cross-entropy and a modified form of policy gradient along with Q loss, optimized in an EM setup. The loss behavior in the above setup is shown in the following image:

✨ Features

Benchmarking

For benchmarking purposes, we are using Semantic Evaluation for Text-to-SQL with Distilled Test Suites, an officially accepted evaluation framework for Spider, SParC, and CoSQL proposed by a research team from Yale and Berkeley. The benchmark contains 2200 test data points. You can run the evaluation using the following link:

Test Suite SQL Eval

We have also benchmarked it on Defog Eval, which contains 200 test data points handpicked by the Defog team. Here is the link:

Defog SQL-Eval

The results are shown in the following image:

📦 Installation

pip install transformers

💻 Usage Examples

Prompt

prompt = f"""<schema>{schema}</schema>
<question>{question}</question>
<sql>"""

Basic Usage - PyTorch

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model = AutoModelForCausalLM.from_pretrained("PipableAI/pip-sql-1.3b")
tokenizer = AutoTokenizer.from_pretrained("PipableAI/pip-sql-1.3b")

inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True).split('<sql>')[1].split('</sql>')[0])

Advanced Usage - Flax

from transformers import FlaxAutoModelForCausalLM, AutoTokenizer
device = "cuda"
model = FlaxAutoModelForCausalLM.from_pretrained("PipableAI/pip-sql-1.3b", from_pt=True)
tokenizer = AutoTokenizer.from_pretrained("PipableAI/pip-sql-1.3b")

inputs = tokenizer(text, return_tensors="jax")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True).split('<sql>')[1].split('</sql>')[0])

📚 Documentation

Schema

CREATE TABLE Products (
  product_id number,
  parent_product_id number,
  product_name text,
  product_price number,
  product_color text,
  product_size text,
  product_description text);

CREATE TABLE Customers (
  customer_id number,
  gender_code text,
  customer_first_name text,
  customer_middle_initial text,
  customer_last_name text,
  email_address text,
  login_name text,
  login_password text,
  phone_number text,
  address_line_1 text,
  town_city text,
  county text,
  country text);

CREATE TABLE Customer_Payment_Methods (
  customer_id number,
  payment_method_code text);

CREATE TABLE Invoices (
  invoice_number number,
  invoice_status_code text,
  invoice_date time);

CREATE TABLE Orders (
  order_id number,
  customer_id number,
  order_status_code text,
  date_order_placed time);

CREATE TABLE Order_Items (
  order_item_id number,
  product_id number,
  order_id number,
  order_item_status_code text);

CREATE TABLE Shipments (
  shipment_id number,
  order_id number,
  invoice_number number,
  shipment_tracking_number text,
  shipment_date time);

CREATE TABLE Shipment_Items (
  shipment_id number,
  order_item_id number);

Questions

What are the email address, town and county of the customers who are of the least common gender?

SELECT email_address ,  town_city ,  county FROM customers GROUP BY gender_code ORDER BY count(*) ASC LIMIT 1

What are the product price and the product size of the products whose price is above average?

SELECT product_price ,  product_size FROM products WHERE product_price  > (SELECT avg(product_price) FROM products)

Which customers did not make any orders? List the first name, middle initial and last name.

SELECT T1.customer_first_name ,  T1.customer_middle_initial ,  T1.customer_last_name FROM Customers AS T1 WHERE T1.customer_id NOT IN (SELECT T2.customer_id FROM Orders AS T2)

🔧 Technical Details

We used softmax cross-entropy and a modified form of policy gradient along with Q loss, optimized in an EM setup.

📄 License

The model is open source under the Apache 2.0 License.

👥 Team

Avi Kothari, Pratham Gupta, Ritvik Aryan Kalra, Rohan Bhatial, Soham Acharya

Additional Information