This is a t5-small fine-tuned version on the wikisql dataset for English to SQL translation text2text mission.

To load the model: (necessary packages: !pip install transformers sentencepiece)

from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("dbernsohn/t5_wikisql_en2SQL")
model = AutoModelWithLMHead.from_pretrained("dbernsohn/t5_wikisql_en2SQL")

You can then use this model to translate SQL queries into plain english.

query = "what are the names of all the people in the USA?"
input_text = f"translate English to Sql: {query} </s>"
features = tokenizer([input_text], return_tensors='pt')

output = model.generate(input_ids=features['input_ids'].cuda(), 
                        attention_mask=features['attention_mask'].cuda())

tokenizer.decode(output[0])
# Output: "SELECT Name FROM table WHERE Country = USA"

The whole training process and hyperparameters are in my GitHub repo

Created by Dor Bernsohn

New: fine-tune this model in a few clicks by selecting AutoNLP in the "Train" menu!
Downloads last month
89
Hosted inference API
Text2Text Generation
This model can be loaded on the Inference API on-demand.