|
|
--- |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
# FLAN-T5 Base Text to SQL Model |
|
|
|
|
|
This model was fine-tuned on [Google's FLAN-T5 base](https://huggingface.co/google/flan-t5-base) using [SParC](https://yale-lily.github.io/sparc), [Spider](https://yale-lily.github.io/spider), and [CoSQL](https://yale-lily.github.io/cosql) datasets. |
|
|
|
|
|
Purpose of this model is to create SQL queries from natural-language text. |
|
|
|
|
|
In order to achieve accuracte results, database schema was incorporated to the prompt during training. |
|
|
|
|
|
GitHub repository can be found [here](https://github.com/alpecevit/text2sql). |
|
|
|
|
|
## Requirements |
|
|
|
|
|
```bash |
|
|
pip install transformers==4.38.2 |
|
|
pip install torch==2.2.2 |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
|
|
|
Please exercise caution when formatting the input. |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("alpecevit/flan-t5-base-text2sql") |
|
|
model = AutoModelForSeq2SeqLM.from_pretrained("alpecevit/flan-t5-base-text2sql") |
|
|
|
|
|
input_text = """ |
|
|
transform question and schema to SQL query. question: Who are the top 5 most paid employess by first name, last name, and salary ? schema: employee(salary, bdate, dno, ssn, fname, sex, superssn, address, minit, lname), department(dnumber, mgrstartdate, dname, mgrssn), dept_locations(dnumber, dlocation), project(pnumber, dnum, pname, plocation), works_on(pno, hours, essn), dependent(bdate, essn, dependent_name, sex, relationship). |
|
|
""" |
|
|
|
|
|
token_input = tokenizer(input_text, return_tensors="pt").input_ids |
|
|
output = model.generate(token_input, max_new_tokens=128) |
|
|
query = tokenizer.decode(output[0], skip_special_tokens=True) |
|
|
|
|
|
print("Predicted Query:", query) |
|
|
``` |
|
|
|
|
|
*Output:* |
|
|
|
|
|
``` |
|
|
SELECT fname, lname, salary FROM employee ORDER BY salary DESC LIMIT 5 |
|
|
``` |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
The fine-tuned model was evaluated using the combination of test splits of the above datasets. [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge) metrics were utilized for the assessment, and the results are outlined below. |
|
|
|
|
|
``` |
|
|
{'rouge1': 0.8740305983060861, 'rouge2': 0.7763397400315798, 'rougeL': 0.8449832130213266, 'rougeLsum': 0.8447120646910007} |
|
|
``` |
