基于变压器的语言模型应用于自然语言处理的广泛应用程序。但是，它们效率低，难以部署。近年来，已经提出了许多压缩算法来提高目标硬件上大型变压器的模型的实现效率。在这项工作中，我们通过整合体重修剪和模型蒸馏来提出一种训练稀疏预训练的变压器语言模型的新方法。这些稀疏的预训练型号可用于在维护稀疏模式的同时传输广泛的任务。我们展示了我们有三个已知的架构的方法，以创建稀疏的预训练伯特基，BERT-MAT​​RY和DISTOLBERT。我们展示了压缩稀疏的预训练模型如何培训他们的知识，以最小的精度损失将他们的知识转移到五种不同的下游自然语言任务。此外，我们展示了如何使用量化感知培训进一步将稀疏模型的重量压缩为8位精度。例如，在SQUAdv1.1上使用我们稀疏预训练的BERT频率，并量化为8位，我们为编码器达到40美元的压缩比，而不是1 \％$精度损失。据我们所知，我们的结果表明Bert-Base，Bert-Light和Distilbert的最佳压缩至准确率。

We revisit the performance of the classic gradual magnitude pruning (GMP) baseline for large language models, focusing on the classic BERT benchmark on various popular tasks. Despite existing evidence in the literature that GMP performs poorly, we show that a simple and general variant, which we call GMP*, can match and sometimes outperform more complex state-of-the-art methods. Our results provide a simple yet strong baseline for future work, highlight the importance of parameter tuning for baselines, and even improve the performance of the state-of-the-art second-order pruning method in this setting.

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-theedge and/or under constrained computational training or inference budgets remains challenging. In this work, we propose a method to pre-train a smaller generalpurpose language representation model, called DistilBERT, which can then be finetuned with good performances on a wide range of tasks like its larger counterparts. While most prior work investigated the use of distillation for building task-specific models, we leverage knowledge distillation during the pre-training phase and show that it is possible to reduce the size of a BERT model by 40%, while retaining 97% of its language understanding capabilities and being 60% faster. To leverage the inductive biases learned by larger models during pre-training, we introduce a triple loss combining language modeling, distillation and cosine-distance losses. Our smaller, faster and lighter model is cheaper to pre-train and we demonstrate its capabilities for on-device computations in a proof-of-concept experiment and a comparative on-device study.

量化，知识蒸馏和修剪是NLP中神经网络压缩的最流行方法之一。独立地，这些方法降低了模型的大小并可以加速推断，但是尚未严格研究它们的相对益处和组合相互作用。对于这些技术的八个可能子集中的每一个，我们比较了六个BERT体系结构和八个胶水任务的准确性与模型大小的权衡。我们发现量化和蒸馏始终比修剪更大的好处。出乎意料的是，除了将多种方法一起使用多种修剪和量化之外，很少会产生回报的减少。取而代之的是，我们观察到互补和超级义务减少了模型大小。我们的工作定量表明，结合压缩方法可以协同降低模型大小，并且从业者应优先考虑（1）量化，（2）知识蒸馏，（3）修剪以最大程度地提高准确性与模型大小的权衡。

预先接受的语言模型（PLMS）在预训练和微调范式下，在各种自然语言处理（NLP）任务中取得了巨大成功。具有大量参数，PLMS是计算密集型和资源饥饿的。因此，已经引入了模型修剪来压缩大规模的PLM。然而，大多数先前的方法只考虑对下游任务的任务特定知识，但忽略了修剪期间的基本任务无关知识，这可能导致灾难性的遗忘问题并导致普遍性较差。为了在我们的修剪模型中维护任务不可行的特定知识，我们提出了在预训练和微调范式下的对比修剪（盖子）。它设计为一​​般框架，与结构化和非结构化修剪兼容。统一的对比学习，CAP使修剪模型能够从预训练的模型中学到任务无关的知识，以及特定于任务知识的微调模型。此外，为了更好地保留修剪模型的性能，快照（即，每个修剪迭代的中间模型）也是修剪的有效监督。我们广泛的实验表明，采用盖子一致地产生显着的改善，特别是在极高的稀疏性方案中。只有3％的型号参数保留（即97％的稀疏性），CAP成功达到了QQP和MNLI任务的原始BERT性能的99.2％和96.3％。此外，我们的探测实验表明，CAP修剪的模型趋于达到更好的泛化能力。

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resourcerestricted devices. To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based models. By leveraging this new KD method, the plenty of knowledge encoded in a large "teacher" BERT can be effectively transferred to a small "student" Tiny-BERT. Then, we introduce a new two-stage learning framework for TinyBERT, which performs Transformer distillation at both the pretraining and task-specific learning stages. This framework ensures that TinyBERT can capture the general-domain as well as the task-specific knowledge in BERT. TinyBERT 41 with 4 layers is empirically effective and achieves more than 96.8% the performance of its teacher BERT BASE on GLUE benchmark, while being 7.5x smaller and 9.4x faster on inference. TinyBERT 4 is also significantly better than 4-layer state-of-the-art baselines on BERT distillation, with only ∼28% parameters and ∼31% inference time of them. Moreover, TinyBERT 6 with 6 layers performs on-par with its teacher BERT BASE .

大型的语言模型（PRELMS）正在彻底改变所有基准的自然语言处理。但是，它们的巨大尺寸对于小型实验室或移动设备上的部署而言是过分的。修剪和蒸馏等方法可减少模型尺寸，但通常保留相同的模型体系结构。相反，我们探索了蒸馏预告片中的更有效的架构，单词的持续乘法（CMOW），该构造将每个单词嵌入为矩阵，并使用矩阵乘法来编码序列。我们扩展了CMOW体系结构及其CMOW/CBOW-HYBRID变体，具有双向组件，以提供更具表现力的功能，在预绘制期间进行一般（任务无义的）蒸馏的单次表示，并提供了两种序列编码方案，可促进下游任务。句子对，例如句子相似性和自然语言推断。我们的基于矩阵的双向CMOW/CBOW-HYBRID模型在问题相似性和识别文本范围内的Distilbert具有竞争力，但仅使用参数数量的一半，并且在推理速度方面快三倍。除了情感分析任务SST-2和语言可接受性任务COLA外，我们匹配或超过ELMO的ELMO分数。但是，与以前的跨架结构蒸馏方法相比，我们证明了检测语言可接受性的分数增加了一倍。这表明基于基质的嵌入可用于将大型预赛提炼成竞争模型，并激励朝这个方向进行进一步的研究。

Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile computing. Efficient NLP research aims to comprehensively consider computation, time and carbon emission for the entire life-cycle of NLP, including data preparation, model training and inference. In this survey, we focus on the inference stage and review the current state of model compression and acceleration for pretrained language models, including benchmarks, metrics and methodology.

基于变压器的NLP模型是使用数亿甚至数十亿个参数训练的，从而限制了其在计算受限环境中的适用性。尽管参数的数量通常与性能相关，但尚不清楚下游任务是否需要整个网络。在最新的修剪和提炼预培训模型的工作中，我们探索了在预训练模型中放下层的策略，并观察修剪对下游胶水任务的影响。我们能够修剪Bert，Roberta和XLNet型号高达40％，同时保持其原始性能的98％。此外，我们证明，在大小和性能方面，您的修剪模型与使用知识蒸馏的型号相提并论。我们的实验产生有趣的观察结果，例如（i）下层对于维持下游任务性能最重要，（ii）某些任务（例如释义检测和句子相似性）对于降低层的降低和（iii）经过训练的模型更强大。使用不同的目标函数表现出不同的学习模式，并且层掉落。

Pre-trained language models achieve superior performance, but they are computationally expensive due to their large size. Techniques such as pruning and knowledge distillation (KD) have been developed to reduce their size and latency. In most structural pruning methods, the pruning units, such as attention heads and feed-forward hidden dimensions, only span a small model structure space and limit the structures that the pruning algorithm can explore. In this work, we propose Gradient-based Intra-attention pruning (GRAIN), which inspects fine intra-attention structures, and allows different heads to have different sizes. Intra-attention pruning greatly expands the searching space of model structures and yields highly heterogeneous structures. We further propose structure regularization to encourage generating more regular structures, which achieves higher speedups than heterogeneous ones. We also integrate KD into the pruning process with a gradient separation strategy to reduce the interference of KD with the pruning process. GRAIN is evaluated on a variety of tasks. Results show that it notably outperforms other methods at the same or similar model size. Even under extreme compression where only $3\%$ weights in transformers remain, the pruned model is still competitive.

存在多种自然语言处理（NLP）任务的多种效率方法，例如修剪，蒸馏，动态推断，量化等。我们可以将效率方法视为应用于模型的操作员。自然，我们可以构建多个效率方法的管道，即，顺序将多个操作员应用于模型。在本文中，我们研究了这一想法的合理性，更重要的是，效率运营商的合理性和累积性。我们做出了两个有趣的观察结果：（1）效率运营商是可交换的 - 管道中效率方法的顺序对最终结果几乎没有影响；（2）效率运算符也是累积的 - 结合几种效率方法的最终结果可以通过组合单个方法的结果来估算。这些观察结果加深了我们对效率运营商的理解，并为其现实世界应用提供了有用的准则。

在生物医学语料库中预先培训的语言模型，例如Biobert，最近在下游生物医学任务上显示出令人鼓舞的结果。另一方面，由于嵌入尺寸，隐藏尺寸和层数等因素，许多现有的预训练模型在资源密集型和计算上都是沉重的。自然语言处理（NLP）社区已经制定了许多策略来压缩这些模型，利用修剪，定量和知识蒸馏等技术，从而导致模型更快，更小，随后更易于使用。同样，在本文中，我们介绍了六种轻型模型，即Biodistilbert，Biotinybert，BioMobilebert，Distilbiobert，Tinybiobert和Cmpactactbiobert，并通过掩护的语言在PubMed DataSet上通过掩护数据进行了知识蒸馏而获得的知识蒸馏来获得。建模（MLM）目标。我们在三个生物医学任务上评估了所有模型，并将它们与Biobert-V1.1进行比较，以创建有效的轻量级模型，以与较大的对应物相同。所有模型将在我们的HuggingFace配置文件上公开可用，网址为https://huggingface.co/nlpie，用于运行实验的代码将在https://github.com/nlpie-research/compact-compact-biomedical-transformers上获得。

将最新的变压器模型蒸馏成轻量级的学生模型是降低推理时计算成本的有效方法。学生模型通常是紧凑的变压器，参数较少，而昂贵的操作（例如自我发项）持续存在。因此，对于实时或大量用例，提高的推理速度仍然不令人满意。在本文中，我们旨在通过将教师模型提炼成更大，更稀疏的学生模型来进一步推动推理速度的极限 - 更大的是它们扩展到数十亿个参数；稀疏，大多数模型参数是N-gram嵌入。我们对六个单词文本分类任务的实验表明，这些学生模型平均保留了罗伯塔大师教师表现的97％，同时推理时GPU和CPU的加速速度最高为600倍。进一步的调查表明，我们的管道也有助于句子对分类任务和域泛化设置。

近年来，大型预训练的变压器网络已显示出许多自然语言理解任务的巨大改进。但是，由于延迟和成本限制，这些模型的巨大规模给他们的微调和在线部署带来了重大挑战。支持N：M半结构化的稀疏性和低精油整数计算的新硬件是提高DNN模型效率的有前途解决方案。但是，很少有研究系统地研究预先训练的变压器网络在多大程度上受益于这些技术的组合，以及如何最好地压缩变压器的每个组件。我们提出了一个灵活的压缩框架NXMiformer，该框架使用ADMM和基于Ste的QAT执行同时进行稀疏和量化。此外，我们介绍且廉价的启发式驱动搜索算法，该算法标识了满足压缩比约束的有希望的异质压缩配置。当通过NLU基准测试的胶水套件进行评估时，我们的方法可以达到BERT模型编码器的93％压缩，同时保留了98.2％的原始模型准确性并充分利用硬件功能。异质配置通过搜索启发式发现了基线准确性的99.5％，同时仍将模型压缩为87.5％。

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications.BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

基于变压器的大型模型在各种自然语言处理和计算机视觉任务中表现出卓越的性能。但是，这些模型包含大量参数，这些参数将其部署限制为现实世界应用程序。为了减少模型大小，研究人员根据权重的重要性得分修剪这些模型。但是，这种分数通常在训练过程中估计在小批次上，这会由于迷你批次采样和复杂的训练动力学而产生巨大的可变性/不确定性。结果，由于这种不确定性，可以通过常用的修剪方法来修剪一些关键权重，从而使训练不稳定并受到概括。为了解决这个问题，我们提出了Platon，该问题通过对重要性估计的上限（UCB）捕获了重要性得分的不确定性。特别是，对于较低的分数但不确定性较高的权重，柏拉图倾向于保留它们并探索其能力。我们对基于自然语言的理解，问答和图像分类的几种基于变压器的模型进行了广泛的实验，以验证柏拉图的有效性。结果表明，柏拉图在不同的稀疏度水平下显着改善。我们的代码可在https://github.com/qingruzhang/platon上公开获取。

在本文中，我们探讨了构建统一基础模型的可能性，该模型可以适应愿景和仅文本任务。从BERT和VIT开始，我们设计一个由模态特定标记，共享变压器编码器和任务特定的输出头组成的统一变压器。为了有效地预先列车在未配对的图像和文本上联合培训拟议的模型，我们提出了两种新颖的技术：（i）我们使用单独培训的BERT和VIT模型作为老师，并应用知识蒸馏，为关节提供额外的准确的监督信号训练; （ii）我们提出了一种新颖的渐变掩蔽策略，以平衡图像和文本预培训损失的参数更新。我们通过微调它分别在图像分类任务和自然语言理解任务上进行微调，评估联合预训练的变压器。实验表明，由此产生的统一基础变压器令人惊讶地在视觉和仅文本任务中令人惊讶地令人惊讶，并且所提出的知识蒸馏和梯度掩蔽策略可以有效地提升分别训练模型水平的性能。

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher model for every new dataset. Alternatively, one may directly work on the improvement of the optimization procedure of the compact model toward better generalization. Recent works observe that the flatness of the local minimum correlates well with better generalization. In this work, we adapt Stochastic Weight Averaging (SWA), a method encouraging convergence to a flatter minimum, to fine-tuning PLMs. We conduct extensive experiments on various NLP tasks (text classification, question answering, and generation) and different model architectures and demonstrate that our adaptation improves the generalization without extra computation cost. Moreover, we observe that this simple optimization technique is able to outperform the state-of-the-art KD methods for compact models.

随着对深度学习民主化的向往，在资源约束设备上实施基于变压器的自然语言处理（NLP）模型的需求越来越大，以实施低延迟和高准确性。现有的BERT修剪方法要求域专家启发手工制作超参数，以在模型大小，延迟和准确性之间取得平衡。在这项工作中，我们提出了AE-Bert，这是一种具有有效评估的自动和高效的BERT修剪框架，以选择“良好”子网络候选（高精度），鉴于整体修剪比率的约束。我们提出的方法不需要人类专家的经验，并且可以在许多NLP任务上取得更好的准确性能。我们关于一般语言理解评估（胶水）基准的实验结果表明，AE-Bert优于Bert $ _ {\ Mathrm {base}} $的最先进的（SOTA）手工制作的修剪方法。在QNLI和RTE上，我们获得75 \％和42.8％的总体修剪比，同时获得更高的精度。在MRPC上，我们的得分比SOTA高4.6，在相同的整体修剪比为0.5。在STS-B上，与SOTA手工制作的修剪方法相比，我们可以达到40 \％的修剪比，而Spearman相关性的损失非常小。实验结果还表明，在模型压缩之后，单个bert $ _ {\ mathrm {base}} $ coder的推理时间在xilinx alveo u200 fpga板上具有1.83 $ \ times $ speedup，与intel（r）xeon相比）Gold 5218（2.30GHz）CPU，它显示了部署BERT $ _ {\ MATHRM {base}} $模型在计算限制设备上生成的方法生成的子网的合理性。

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer models from being used in production. To address this gap, model compression techniques such as quantization and pruning may be used to improve inference efficiency. However, these compression techniques require specialized software to apply and deploy at scale. In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators. We demonstrate the efficiency of our pipeline by creating a Fast DistilBERT model showing minimal accuracy loss on the question-answering SQuADv1.1 benchmark, and throughput results under typical production constraints and environments. Our results outperform existing state-of-the-art Neural Magic's DeepSparse runtime performance by up to 50% and up to 4.1x performance speedup over ONNX Runtime. Source code is publicly available at https://github.com/intel/intel-extension-for-transformers.