اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBinaryBERT: Pushing the Limit of BERT Quantization
382
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks.
قيم البحث
اقرأ أيضاً
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 efficient inference at the ed
ge, 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.
Recently, generative data-free quantization emerges as a practical approach that compresses the neural network to low bit-width without access to real data. It generates data to quantize the network by utilizing the batch normalization (BN) statistic
s of its full-precision counterpart. However, our study shows that in practice, the synthetic data completely constrained by BN statistics suffers severe homogenization at distribution and sample level, which causes serious accuracy degradation of the quantized network. This paper presents a generic Diverse Sample Generation (DSG) scheme for the generative data-free post-training quantization and quantization-aware training, to mitigate the detrimental homogenization. In our DSG, we first slack the statistics alignment for features in the BN layer to relax the distribution constraint. Then we strengthen the loss impact of the specific BN layer for different samples and inhibit the correlation among samples in the generation process, to diversify samples from the statistical and spatial perspective, respectively. Extensive experiments show that for large-scale image classification tasks, our DSG can consistently outperform existing data-free quantization methods on various neural architectures, especially under ultra-low bit-width (e.g., 22% gain under W4A4 setting). Moreover, data diversifying caused by our DSG brings a general gain in various quantization methods, demonstrating diversity is an important property of high-quality synthetic data for data-free quantization.
We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than Quantization-Aw
are Training (QAT). In this work, we propose a novel PTQ framework, dubbed BRECQ, which pushes the limits of bitwidth in PTQ down to INT2 for the first time. BRECQ leverages the basic building blocks in neural networks and reconstructs them one-by-one. In a comprehensive theoretical study of the second-order error, we show that BRECQ achieves a good balance between cross-layer dependency and generalization error. To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity. Extensive experiments on various handcrafted and searched neural architectures are conducted for both image classification and object detection tasks. And for the first time we prove that, without bells and whistles, PTQ can attain 4-bit ResNet and MobileNetV2 comparable with QAT and enjoy 240 times faster production of quantized models. Codes are available at https://github.com/yhhhli/BRECQ.
Recently, transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. However, these language models usually are computation expensive and memory intensive during infe
rence. As a result, it is difficult to deploy them on resource-restricted devices. To improve the inference performance, as well as reduce the model size while maintaining the model accuracy, we propose a novel quantization method named KDLSQ-BERT that combines knowledge distillation (KD) with learned step size quantization (LSQ) for language model quantization. The main idea of our method is that the KD technique is leveraged to transfer the knowledge from a teacher model to a student model when exploiting LSQ to quantize that student model during the quantization training process. Extensive experiment results on GLUE benchmark and SQuAD demonstrate that our proposed KDLSQ-BERT not only performs effectively when doing different bit (e.g. 2-bit $sim$ 8-bit) quantization, but also outperforms the existing BERT quantization methods, and even achieves comparable performance as the full-precision base-line model while obtaining 14.9x compression ratio. Our code will be public available.
Chemically Peculiar (CP) stars have been subject of systematic research since more than 50 years. With the discovery of pulsation of some of the cool CP stars, the availability of advanced spectropolarimetric instrumentation and high signal- to-noise
, high resolution spectroscopy, a new era of CP star research emerged about 20 years ago. Together with the success in ground-based observations, new space projects are developed that will greatly benefit for future investigations of these unique objects. In this contribution we will give an overview of some interesting results obtained recently from ground-based observations and discuss on future outstanding Gaia space mission and its impact on CP star research.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
