3.4 KiB
I-BERT
Overview
The I-BERT model was proposed in I-BERT: Integer-only BERT Quantization by Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney and Kurt Keutzer. It's a quantized version of RoBERTa running inference up to four times faster.
The abstract from the paper is the following:
Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks. However, their memory footprint, inference latency, and power consumption are prohibitive for efficient inference at the edge, and even at the data center. While quantization can be a viable solution for this, previous work on quantizing Transformer based models use floating-point arithmetic during inference, which cannot efficiently utilize integer-only logical units such as the recent Turing Tensor Cores, or traditional integer-only ARM processors. In this work, we propose I-BERT, a novel quantization scheme for Transformer based models that quantizes the entire inference with integer-only arithmetic. Based on lightweight integer-only approximation methods for nonlinear operations, e.g., GELU, Softmax, and Layer Normalization, I-BERT performs an end-to-end integer-only BERT inference without any floating point calculation. We evaluate our approach on GLUE downstream tasks using RoBERTa-Base/Large. We show that for both cases, I-BERT achieves similar (and slightly higher) accuracy as compared to the full-precision baseline. Furthermore, our preliminary implementation of I-BERT shows a speedup of 2.4 - 4.0x for INT8 inference on a T4 GPU system as compared to FP32 inference. The framework has been developed in PyTorch and has been open-sourced.
This model was contributed by kssteven. The original code can be found here.
Resources
- Text classification task guide
- Token classification task guide
- Question answering task guide
- Masked language modeling task guide
- Multiple choice task guide
IBertConfig
autodoc IBertConfig
IBertModel
autodoc IBertModel - forward
IBertForMaskedLM
autodoc IBertForMaskedLM - forward
IBertForSequenceClassification
autodoc IBertForSequenceClassification - forward
IBertForMultipleChoice
autodoc IBertForMultipleChoice - forward
IBertForTokenClassification
autodoc IBertForTokenClassification - forward
IBertForQuestionAnswering
autodoc IBertForQuestionAnswering - forward