MKQ-BERT: Quantized BERT with 4-bits Weights and Activations

• URL: http://arxiv.org/abs/2203.13483v1
• Date: Fri, 25 Mar 2022 07:27:18 GMT
• Title: MKQ-BERT: Quantized BERT with 4-bits Weights and Activations
• Authors: Hanlin Tang, Xipeng Zhang, Kai Liu, Jianchen Zhu, Zhanhui Kang
• Abstract summary: We propose MKQ-BERT, which further improves the compression level and uses 4-bits for quantization. We are the first work that successfully deploys the 4-bits BERT and achieves an end-to-end speedup for inference.
• Score: 13.687982804234293
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. However, the computational cost for deploying these models is prohibitive on resource-restricted devices. One method to alleviate this computation overhead is to quantize the original model into fewer bits representation, and previous work has proved that we can at most quantize both weights and activations of BERT into 8-bits, without degrading its performance. In this work, we propose MKQ-BERT, which further improves the compression level and uses 4-bits for quantization. In MKQ-BERT, we propose a novel way for computing the gradient of the quantization scale, combined with an advanced distillation strategy. On the one hand, we prove that MKQ-BERT outperforms the existing BERT quantization methods for achieving a higher accuracy under the same compression level. On the other hand, we are the first work that successfully deploys the 4-bits BERT and achieves an end-to-end speedup for inference. Our results suggest that we could achieve 5.3x of bits reduction without degrading the model accuracy, and the inference speed of one int4 layer is 15x faster than a float32 layer in Transformer based model.

Related papers

• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models [58.5019443418822]
  Diffusion models have been proven highly effective at generating high-quality images. As these models grow larger, they require significantly more memory and suffer from higher latency. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits.
  arXiv  Detail & Related papers  (2024-11-07T18:59:58Z)
• HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization [10.307268005739202]
  Diffusion Transformers (DiTs) have recently gained substantial attention for their superior visual generation capabilities. DiTs also come with high parameter counts and implementation costs, seriously restricting their use on resource-limited devices such as mobile phones. We introduce the Hybrid Floating-point Quantization for DiT(HQ-DiT), an efficient post-training quantization method that utilizes 4-bit floating-point (FP) precision on both weights and activations for DiT inference.
  arXiv  Detail & Related papers  (2024-05-30T06:56:11Z)
• TEQ: Trainable Equivalent Transformation for Quantization of LLMs [1.0376648762140632]
  We present TEQ, a trainable equivalent transformation that preserves the FP32 precision of the model output while taking advantage of low-precision quantization. The training process is lightweight, requiring only 1K steps and fewer than 0.1 percent of the original model's trainable parameters.
  arXiv  Detail & Related papers  (2023-10-17T02:42:34Z)
• The case for 4-bit precision: k-bit Inference Scaling Laws [75.4335600212427]
  Quantization methods reduce the number of bits required to represent each parameter in a model. The final model size depends on both the number of parameters of the original model and the rate of compression. We run more than 35,000 zero-shot experiments with 16-bit inputs and k-bit parameters to examine which quantization methods improve scaling for 3 to 8-bit precision.
  arXiv  Detail & Related papers  (2022-12-19T18:48:33Z)
• Prune Once for All: Sparse Pre-Trained Language Models [0.6063525456640462]
  We present a new method for training sparse pre-trained Transformer language models by integrating weight pruning and model distillation. These sparse pre-trained models can be used to transfer learning for a wide range of tasks while maintaining their sparsity pattern. We show how the compressed sparse pre-trained models we trained transfer their knowledge to five different downstream natural language tasks with minimal accuracy loss.
  arXiv  Detail & Related papers  (2021-11-10T15:52:40Z)
• Differentiable Model Compression via Pseudo Quantization Noise [99.89011673907814]
  We propose to add independent pseudo quantization noise to model parameters during training to approximate the effect of a quantization operator. We experimentally verify that our method outperforms state-of-the-art quantization techniques on several benchmarks and architectures for image classification, language modeling, and audio source separation.
  arXiv  Detail & Related papers  (2021-04-20T14:14:03Z)
• KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization [1.9786767260073905]
  transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. We propose a novel quantization method named KDLSQ-BERT that combines knowledge distillation (KD) with learned step size quantization (LSQ) for language model quantization.
  arXiv  Detail & Related papers  (2021-01-15T02:21:28Z)
• I-BERT: Integer-only BERT Quantization [78.43819756382103]
  We propose I-BERT, a novel quantization scheme for Transformer based models. I-BERT performs an end-to-end integer-only BERT inference without any floating point calculation. We show that for both cases, I-BERT achieves similar (and slightly higher) accuracy as compared to the full-precision baseline.
  arXiv  Detail & Related papers  (2021-01-05T02:42:58Z)
• BinaryBERT: Pushing the Limit of BERT Quantization [74.65543496761553]
  We propose BinaryBERT, which pushes BERT quantization to the limit with 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 landscapes. Empirical results show that BinaryBERT has negligible performance drop compared to the full-precision BERT-base.
  arXiv  Detail & Related papers  (2020-12-31T16:34:54Z)
• TernaryBERT: Distillation-aware Ultra-low Bit BERT [53.06741585060951]
  We propose TernaryBERT, which ternarizes the weights in a fine-tuned BERT model. Experiments on the GLUE benchmark and SQuAD show that our proposed TernaryBERT outperforms the other BERT quantization methods.
  arXiv  Detail & Related papers  (2020-09-27T10:17:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.