DuckDB-NSQL-7B-v0.1 / README.md
tdoehmen's picture
[metadata] specify base_model (#1)
c0b4dc0 verified
metadata
license: llama2
inference:
  parameters:
    do_sample: false
    max_length: 200
base_model: meta-llama/Llama-2-7b
widget:
  - text: >-
      ### Instruction:

      Your task is to generate valid duckdb SQL to answer the following
      question.


      ### Input:


      ### Question:

      create a new table called tmp from test.csv


      ### Response (use duckdb shorthand if possible):
    example_title: read test.csv
  - text: >-
      ### Instruction:

      Your task is to generate valid duckdb SQL to answer the following
      question.


      ### Input:


      ### Question:

      create a new table called tmp from test.csv


      ### Response (use duckdb shorthand if possible):
    example_title: get _amount columns
  - text: >-
      ### Instruction:

      Your task is to generate valid duckdb SQL to answer the following
      question, given a duckdb database schema.


      ### Input:

      Here is the database schema that the SQL query will run on:

      CREATE TABLE rideshare (
          hvfhs_license_num varchar,
          dispatching_base_num varchar,
          originating_base_num varchar,
          request_datetime timestamp,
          on_scene_datetime timestamp,
          pickup_datetime timestamp,
          dropoff_datetime timestamp,
          trip_miles double,
          trip_time bigint,

      );


      ### Question:

      get longest trip in december 2022


      ### Response (use duckdb shorthand if possible):
    example_title: taxi trips

DuckDB-NSQL-7B

Model Description

NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.

In this repository we are introducing a new member of NSQL, DuckDB-NSQL. It's based on Meta's original Llama-2 7B model and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of DuckDB text-to-SQL pairs.

Training Data

200k DuckDB text-to-SQL pairs, synthetically generated using Mixtral-8x7B-Instruct-v0.1, guided by the DuckDB v0.9.2 documentation. And text-to-SQL pairs from NSText2SQL that were transpiled to DuckDB SQL using sqlglot.

Evaluation Data

We evaluate our models on a DuckDB-specific benchmark that contains 75 text-to-SQL pairs. The benchmark is available here.

Training Procedure

DuckDB-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 model is trained using 80GB A100s, leveraging data and model parallelism. We 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 outputs. In contrast to existing text-to-SQL models, the SQL generation is not contrained to SELECT statements, but can generate any valid DuckDB SQL statement, including statements for official DuckDB extensions.

How to Use

Example 1:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1", torch_dtype=torch.bfloat16)

text = """### Instruction:
Your task is to generate valid duckdb SQL to answer the following question.

### Input:

### Question:
create a new table called tmp from test.csv

### Response (use duckdb shorthand if possible):
"""

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:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1", torch_dtype=torch.bfloat16)

text = """### Instruction:
Your task is to generate valid duckdb SQL to answer the following question, given a duckdb database schema.

### Input:
Here is the database schema that the SQL query will run on:
CREATE TABLE taxi (
    VendorID bigint,
    tpep_pickup_datetime timestamp,
    tpep_dropoff_datetime timestamp,
    passenger_count double,
    trip_distance double,
    fare_amount double,
    extra double,
    tip_amount double,
    tolls_amount double,
    improvement_surcharge double,
    total_amount double,
);

### Question:
get all columns ending with _amount from taxi table

### Response (use duckdb shorthand if possible):"""

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:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("motherduckdb/DuckDB-NSQL-7B-v0.1", torch_dtype=torch.bfloat16)

text = """### Instruction:
Your task is to generate valid duckdb SQL to answer the following question, given a duckdb database schema.

### Input:
Here is the database schema that the SQL query will run on:
CREATE TABLE rideshare (
    hvfhs_license_num varchar,
    dispatching_base_num varchar,
    originating_base_num varchar,
    request_datetime timestamp,
    on_scene_datetime timestamp,
    pickup_datetime timestamp,
    dropoff_datetime timestamp,
    trip_miles double,
    trip_time bigint,

);

### Question:
get longest trip in december 2022

### Response (use duckdb shorthand if possible):
"""

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.