Back to all models
Model: mrm8488/t5-base-finetuned-squadv2

Monthly model downloads

mrm8488/t5-base-finetuned-squadv2 mrm8488/t5-base-finetuned-squadv2
- downloads
last 30 days

pytorch

tf

Contributed by

mrm8488 Manuel Romero
67 models

How to use this model directly from the πŸ€—/transformers library:

			
Copy model
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-squadv2") model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-squadv2")

T5-base fine-tuned on SQuAD v2

Google's T5 fine-tuned on SQuAD v2 for Q&A downstream task.

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 β€œColossal Clean Crawled Corpus”, 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.

Details of the downstream task (Q&A) - Dataset πŸ“š 🧐 ❓

SQuAD v2 combines the 100,000 questions in SQuAD1.1 with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering.

Dataset Split # samples
SQuAD2.0 train 130k
SQuAD2.0 eval 12.3k

Model fine-tuning πŸ‹οΈβ€

The training script is a slightly modified version of this one

Results πŸ“

Metric # Value
EM 77.64
F1 81.32

Model in Action πŸš€

from transformers import AutoModelWithLMHead, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-squadv2")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-squadv2")

def get_answer(question, context):
  input_text = "question: %s  context: %s </s>" % (question, context)
  features = tokenizer.batch_encode_plus([input_text], return_tensors='pt')

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

  return tokenizer.decode(output[0])

context = "Manuel have created RuPERTa-base with the support of HF-Transformers and Google"
question = "Who has supported Manuel?"

get_answer(question, context)

# output: 'HF-Transformers and Google'

Created by Manuel Romero/@mrm8488 | LinkedIn

Made with in Spain