julien-c's picture
julien-c HF staff
Migrate model card from transformers-repo
e8c643a
metadata
language: en
datasets:
  - wikisql

T5-small fine-tuned on WikiSQL

Google's T5 small fine-tuned on WikiSQL for English to SQL translation.

Details of T5

The T5 model was presented in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu in Here the abstract:

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new โ€œColossal Clean Crawled Corpusโ€, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.

model image

Details of the Dataset ๐Ÿ“š

Dataset ID: wikisql from Huggingface/NLP

Dataset Split # samples
wikisql train 56355
wikisql valid 14436

How to load it from nlp

train_dataset  = nlp.load_dataset('wikisql', split=nlp.Split.TRAIN)
valid_dataset = nlp.load_dataset('wikisql', split=nlp.Split.VALIDATION)

Check out more about this dataset and others in NLP Viewer

Model fine-tuning ๐Ÿ‹๏ธโ€

The training script is a slightly modified version of this Colab Notebook created by Suraj Patil, so all credits to him!

Model in Action ๐Ÿš€

from transformers import AutoModelWithLMHead, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-small-finetuned-wikiSQL")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-small-finetuned-wikiSQL")

def get_sql(query):
  input_text = "translate English to SQL: %s </s>" % query
  features = tokenizer([input_text], return_tensors='pt')

  output = model.generate(input_ids=features['input_ids'], 
               attention_mask=features['attention_mask'])
  
  return tokenizer.decode(output[0])

query = "How many millions of params there are in HF-hub?"

get_sql(query)

# output: 'SELECT COUNT Params FROM table WHERE Location = HF-hub'

Created by Manuel Romero/@mrm8488 | LinkedIn

Made with โ™ฅ in Spain