This is the set of 24 BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.
BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. Moreover, BigBird comes along with a theoretical understanding of the capabilities of a complete transformer that the sparse model can handle. Disclaimer: The team releasing BigBird did not write a model card for this model so this model card has been written by the Hugging Face team. BigBird relies on **block sparse attention** instead of normal attention (i.e. BERT's attention) and can handle sequences up to a length of 4096 at a much lower compute cost compared to BERT. It has achieved SOTA on various tasks involving very long sequences such as long documents summarization, question-answering with long contexts.
BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. Moreover, BigBird comes along with a theoretical understanding of the capabilities of a complete transformer that the sparse model can handle. It is a pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. Disclaimer: The team releasing BigBird did not write a model card for this model so this model card has been written by the Hugging Face team.
BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. Moreover, BigBird comes along with a theoretical understanding of the capabilities of a complete transformer that the sparse model can handle. It is a pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. Disclaimer: The team releasing BigBird did not write a model card for this model so this model card has been written by the Hugging Face team.
The BiT model was proposed in Big Transfer (BiT): General Visual Representation Learning by Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby. BiT is a simple recipe for scaling up pre-training of ResNet-like architectures (specifically, ResNetv2). The method results in significant improvements for transfer learning. Disclaimer: The team releasing ResNet did not write a model card for this model so this model card has been written by the Hugging Face team. *Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -- from 1 example per class to 1M total examples. BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB). On small datasets, BiT attains 76.8% on ILSVRC-2012 with 10 examples per class, and 97.0% on CIFAR-10 with 10 examples per class. We conduct detailed analysis of the main components that lead to high transfer performance.*
ByT5 is a tokenizer-free version of Google's T5 and generally follows the architecture of MT5. ByT5 was only pre-trained on mC4 excluding any supervised training with an average span-mask of 20 UTF-8 characters. Therefore, this model has to be fine-tuned before it is useable on a downstream task. ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-base` significantly outperforms mt5-base on TweetQA.
ByT5 was only pre-trained on mC4 excluding any supervised training with an average span-mask of 20 UTF-8 characters. Therefore, this model has to be fine-tuned before it is useable on a downstream task. ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-large` significantly outperforms mt5-large on TweetQA. Authors: *Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel*
ByT5 is a tokenizer-free version of Google's T5 and generally follows the architecture of MT5. ByT5 was only pre-trained on mC4 excluding any supervised training with an average span-mask of 20 UTF-8 characters. Therefore, this model has to be fine-tuned before it is useable on a downstream task. ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-small` significantly outperforms mt5-small on TweetQA.
Pretrained CANINE model on 104 languages using a masked language modeling (MLM) objective. It was introduced in the paper CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation and first released in this repository. What's special about CANINE is that it doesn't require an explicit tokenizer (such as WordPiece or SentencePiece) as other models like BERT and RoBERTa. Instead, it directly operates at a character level: each character is turned into its Unicode code point. This means that input processing is trivial and can typically be accomplished as:
Pretrained CANINE model on 104 languages using a masked language modeling (MLM) objective. It was introduced in the paper CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation and first released in this repository. What's special about CANINE is that it doesn't require an explicit tokenizer (such as WordPiece or SentencePiece) as other models like BERT and RoBERTa. Instead, it directly operates at a character level: each character is turned into its Unicode code point. Disclaimer: The team releasing CANINE did not write a model card for this model so this model card has been written by the Hugging Face team.
