Hugging Face's logo

SwastikM
/
bart-large-nl2sql

Text2Text Generation
Transformers
Safetensors
English
bart
natural language
SQL
text2sql
nl2sql
Eval Results
Inference Endpoints
Model card Files Community
bart-large-nl2sql / README.md
SwastikM's picture
SwastikM
Update README.md
36a509d verified
preview code
|
raw
history blame
6.44 kB
metadata
widget:
  - text: >-
      sql_prompt: What is the monthly voice usage for each customer in the
      Mumbai region? sql_context: CREATE TABLE customers (customer_id INT, name
      VARCHAR(50), voice_usage_minutes FLOAT, region VARCHAR(50)); INSERT INTO
      customers (customer_id, name, voice_usage_minutes, region) VALUES (1,
      'Aarav Patel', 500, 'Mumbai'), (2, 'Priya Shah', 700, 'Mumbai');
    example_title: Example1
  - text: >-
      sql_prompt: How many wheelchair accessible vehicles are there in the
      'Train' mode of transport? sql_context: CREATE TABLE Vehicles(vehicle_id
      INT, vehicle_type VARCHAR(20), mode_of_transport VARCHAR(20),
      is_wheelchair_accessible BOOLEAN); INSERT INTO Vehicles(vehicle_id,
      vehicle_type, mode_of_transport, is_wheelchair_accessible) VALUES (1,
      'Train_Car', 'Train', TRUE), (2, 'Train_Engine', 'Train', FALSE), (3,
      'Bus', 'Bus', TRUE);
    example_title: Example2
  - text: >-
      sql_prompt: Which economic diversification efforts in the
      'diversification' table have a higher budget than the average budget for
      all economic diversification efforts in the 'budget' table? sql_context:
      CREATE TABLE diversification (id INT, effort VARCHAR(50), budget FLOAT);
      CREATE TABLE budget (diversification_id INT, diversification_effort
      VARCHAR(50), amount FLOAT);
    example_title: Example3
language:
  - en
datasets:
  - gretelai/synthetic_text_to_sql
metrics:
  - rouge
library_name: transformers
base_model: facebook/bart-large-cnn
model-index:
  - name: SwastikM/bart-large-nl2sql
    results:
      - task:
          type: text2text-generation
        dataset:
          name: gretelai/synthetic_text_to_sql
          type: gretelai/synthetic_text_to_sql
          split: train, test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 55.69
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 42.99
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 51.43
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 51.4
            verified: true

BART (large-sized model), fine-tuned on synthetic_text_to_sql

Generate SQL from Natural Language question with a SQL context.

Model Details

Model Description

BART from facebook/bart-large-cnn is fintuned on gretelai/synthetic_text_to_sql dataset to generate SQL from NL and SQL context

Intended uses & limitations

Addressing the power of LLM in fintuned downstream task. Implemented as a personal Project.

How to use

Load model directly 

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("SwastikM/bart-large-nl2sql")

model = AutoModelForSeq2SeqLM.from_pretrained("SwastikM/bart-large-nl2sql")

query_question_with_context = """sql_prompt: Which economic diversification efforts in
the 'diversification' table have a higher budget than the average budget for all economic diversification efforts in the 'budget' table?
sql_context: CREATE TABLE diversification (id INT, effort VARCHAR(50), budget FLOAT); CREATE TABLE
budget (diversification_id INT, diversification_effort VARCHAR(50), amount FLOAT);"""

sql = model.generate(text)

print(sql)

Training Details

Training Data

gretelai/synthetic_text_to_sql

Training Procedure

HuggingFace Accelerate with Training Loop.

Preprocessing

  • Encoder Input: "sql_prompt: " + data['sql_prompt']+" sql_context: "+data['sql_context']
  • Decoder Input: data['sql']

Training Hyperparameters

  • Optimizer: AdamW
  • lr: 2e-5
  • decay: linear
  • num_warmup_steps: 0
  • batch_size: 8
  • num_training_steps: 12500

Evaluation

Rouge Score

  • Rouge1: 55.69
  • Rouge2: 42.99
  • RougeL: 51.43
  • RougeLsum: 51.40

Hardware

  • GPU: P100

Citing Dataset and BaseModel 

  @software{gretel-synthetic-text-to-sql-2024,
  author = {Meyer, Yev and Emadi, Marjan and Nathawani, Dhruv and Ramaswamy, Lipika and Boyd, Kendrick and Van Segbroeck, Maarten and Grossman, Matthew and Mlocek, Piotr and Newberry, Drew},
  title = {{Synthetic-Text-To-SQL}: A synthetic dataset for training language models to generate SQL queries from natural language prompts},
  month = {April},
  year = {2024},
  url = {https://huggingface.co/datasets/gretelai/synthetic-text-to-sql}
}

@article{DBLP:journals/corr/abs-1910-13461,
  author    = {Mike Lewis and
               Yinhan Liu and
               Naman Goyal and
               Marjan Ghazvininejad and
               Abdelrahman Mohamed and
               Omer Levy and
               Veselin Stoyanov and
               Luke Zettlemoyer},
  title     = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language
               Generation, Translation, and Comprehension},
  journal   = {CoRR},
  volume    = {abs/1910.13461},
  year      = {2019},
  url       = {http://arxiv.org/abs/1910.13461},
  eprinttype = {arXiv},
  eprint    = {1910.13461},
  timestamp = {Thu, 31 Oct 2019 14:02:26 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1910-13461.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Model Card Authors

Swastik Maiti