--- 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 github: https://github.com/swastikmaiti/SwastikM-bart-large-nl2sql.git co2_eq_emissions: emissions: 160 source: "[ML CO2 Impact](https://mlco2.github.io/impact/#home)" training_type: "fine-tuning" hardware_used: "TESLA P100" tags: - natural language - SQL - text2sql - nl2sql --- # BART-LARGE-CNN fine-tuned on SYNTHETIC_TEXT_TO_SQL Generate SQL query 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 - **Model type:** BART - **Language(s) (NLP):** English - **License:** openrail - **Finetuned from model [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn?text=The+tower+is+324+metres+%281%2C063+ft%29+tall%2C+about+the+same+height+as+an+81-storey+building%2C+and+the+tallest+structure+in+Paris.+Its+base+is+square%2C+measuring+125+metres+%28410+ft%29+on+each+side.+During+its+construction%2C+the+Eiffel+Tower+surpassed+the+Washington+Monument+to+become+the+tallest+man-made+structure+in+the+world%2C+a+title+it+held+for+41+years+until+the+Chrysler+Building+in+New+York+City+was+finished+in+1930.+It+was+the+first+structure+to+reach+a+height+of+300+metres.+Due+to+the+addition+of+a+broadcasting+aerial+at+the+top+of+the+tower+in+1957%2C+it+is+now+taller+than+the+Chrysler+Building+by+5.2+metres+%2817+ft%29.+Excluding+transmitters%2C+the+Eiffel+Tower+is+the+second+tallest+free-standing+structure+in+France+after+the+Millau+Viaduct.)** - **Dataset:** [gretelai/synthetic_text_to_sql](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql) ## Intended uses & limitations Addressing the power of LLM in fintuned downstream task. Implemented as a personal Project. ### How to use ```python 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);""" ``` # Use a pipeline as a high-level helper ```python from transformers import pipeline sql_generator = pipeline("text2text-generation", model="SwastikM/bart-large-nl2sql") sql = sql_generator(query_question_with_context)[0]['generated_text'] print(sql) ``` # Load model directly ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("SwastikM/bart-large-nl2sql") model = AutoModelForSeq2SeqLM.from_pretrained("SwastikM/bart-large-nl2sql") inputs = tokenizer(query_question_with_context, return_tensors="pt").input_ids outputs = model.generate(inputs, max_new_tokens=100, do_sample=False) sql = tokenizer.decode(outputs[0], skip_special_tokens=True) print(sql) ``` ## Training Details ### Training Data [gretelai/synthetic_text_to_sql](https://huggingface.co/datasets/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 #### 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} } ``` ## Additional Information - ***Github:*** [Repository](https://github.com/swastikmaiti/SwastikM-bart-large-nl2sql.git) ## Acknowledgment Thanks to [@AI at Meta](https://huggingface.co/facebook) for adding the Pre Trained Model. Thanks to [@Gretel.ai](https://huggingface.co/gretelai) for adding the datset. ## Model Card Authors Swastik Maiti