NSQL (NSQL-2B)
Model Description
NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
The checkpoint included in this repository is based on CodeGen-Multi 2B from Salesforce and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs.
Training Data
The general SQL queries are the SQL subset from The Stack, containing 1M training samples. The labeled text-to-SQL pairs come from more than 20 public sources across the web from standard datasets. We hold out Spider and GeoQuery datasets for use in evaluation.
Evaluation Data
We evaluate our models on two text-to-SQL benchmarks : Spider and GeoQuery
Training Procedure
NSQL was trained using cross-entropy loss to maximize the likelihood of sequential inputs. For finetuning on text-to-SQL pairs, we only compute the loss over the SQL portion of the pair. The family of models is trained using 80GB A100s, leveraging data and model parallelism. We pre-trained for 3 epochs and fine-tuned for 10 epochs.
Intended Use and Limitations
The model was designed for text-to-SQL generation tasks from given table schema and natural language prompts. The model works best with the prompt format defined below and outputting SELECT queries.
How to Use
Example 1:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-2B")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-2B")
text = """CREATE TABLE stadium (
stadium_id number,
location text,
name text,
capacity number,
highest number,
lowest number,
average number
)
CREATE TABLE singer (
singer_id number,
name text,
country text,
song_name text,
song_release_year text,
age number,
is_male others
)
CREATE TABLE concert (
concert_id number,
concert_name text,
theme text,
stadium_id text,
year text
)
CREATE TABLE singer_in_concert (
concert_id number,
singer_id text
)
-- Using valid SQLite, answer the following questions for the tables provided above.
-- What is the maximum, the average, and the minimum capacity of stadiums ?
SELECT"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
Example 2:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-2B")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-2B")
text = """CREATE TABLE stadium (
stadium_id number,
location text,
name text,
capacity number,
)
-- Using valid SQLite, answer the following questions for the tables provided above.
-- how many stadiums in total?
SELECT"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
Example 3:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-2B")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-2B")
text = """CREATE TABLE work_orders (
ID NUMBER,
CREATED_AT TEXT,
COST FLOAT,
INVOICE_AMOUNT FLOAT,
IS_DUE BOOLEAN,
IS_OPEN BOOLEAN,
IS_OVERDUE BOOLEAN,
COUNTRY_NAME TEXT,
)
-- Using valid SQLite, answer the following questions for the tables provided above.
-- how many work orders are open?
SELECT"""
input_ids = tokenizer(text, return_tensors="pt").input_ids
generated_ids = model.generate(input_ids, max_length=500)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
For more information (e.g., run with your local database), please find examples in this repository.