MoDification: Mixture of Depths Made Easy

• URL: http://arxiv.org/abs/2410.14268v1
• Date: Fri, 18 Oct 2024 08:22:07 GMT
• Title: MoDification: Mixture of Depths Made Easy
• Authors: Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song,
• Abstract summary: mixture of depths (MoD) is proposed as a perfect fit to bring down both latency and memory. MoDification can achieve up to 1.2x speedup in latency and 1.8x reduction in memory.
• Score: 36.3113087767816
• License:
• Abstract: Long-context efficiency has recently become a trending topic in serving large language models (LLMs). And mixture of depths (MoD) is proposed as a perfect fit to bring down both latency and memory. In this paper, however, we discover that MoD can barely transform existing LLMs without costly training over an extensive number of tokens. To enable the transformations from any LLMs to MoD ones, we showcase top-k operator in MoD should be promoted to threshold-p operator, and refinement to architecture and data should also be crafted along. All these designs form our method termed MoDification. Through a comprehensive set of experiments covering model scales from 3B to 70B, we exhibit MoDification strikes an excellent balance between efficiency and effectiveness. MoDification can achieve up to ~1.2x speedup in latency and ~1.8x reduction in memory compared to original LLMs especially in long-context applications.

Related papers

• $γ-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models [87.43596173378913]
  We propose an innovative strategy for existing MLLMs called $gamma$-MoD. In $gamma$-MoD, a novel metric is proposed to guide the deployment of MoDs in the MLLM. Based on ARank, we propose two novel designs to maximize the computational sparsity of MLLM.
  arXiv  Detail & Related papers  (2024-10-17T17:59:53Z)
• LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation [41.05687297326706]
  LLaVA-MoD is a framework designed to enable the efficient training of small-scale Multimodal Language Models. We optimize the network structure of s-MLLM by integrating a sparse Mixture of Experts architecture into the language model. We also propose a progressive knowledge transfer strategy to ensure comprehensive knowledge migration.
  arXiv  Detail & Related papers  (2024-08-28T15:52:23Z)
• LaDiMo: Layer-wise Distillation Inspired MoEfier [1.6199400106794555]
  We propose a novel algorithm, LaDiMo, which efficiently converts a Transformer-based non-MoE model into a MoE model with minimal additional training cost. We demonstrate the effectiveness of our method by converting the LLaMA2-7B model to a MoE model using only 100K tokens.
  arXiv  Detail & Related papers  (2024-08-08T07:37:26Z)
• MoExtend: Tuning New Experts for Modality and Task Extension [61.29100693866109]
  MoExtend is an effective framework designed to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. MoExtend seamlessly integrates new experts into pre-trained MoE models, endowing them with novel knowledge without the need to tune pretrained models.
  arXiv  Detail & Related papers  (2024-08-07T02:28:37Z)
• Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training [45.97480866595295]
  Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. We adopt a 3D sharding method that keeps the dense-to-MoE step time increase within a healthy range.
  arXiv  Detail & Related papers  (2024-05-23T21:00:53Z)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
  MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
  arXiv  Detail & Related papers  (2024-02-22T18:56:07Z)
• Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs [67.38165028487242]
  We introduce Dynamic Sparse No Training (DSnoT), a training-free fine-tuning approach to fine-tune large language models (LLMs) Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs. Our paper offers fresh insights into how to fine-tune sparse LLMs in an efficient training-free manner and open new venues to scale the great potential of sparsity to LLMs.
  arXiv  Detail & Related papers  (2023-10-13T07:38:52Z)
• Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning [52.29522018586365]
  We study structured pruning as an effective means to develop smaller LLMs from pre-trained, larger models. Our approach employs two key techniques: (1) targeted structured pruning, which prunes a larger model to a specified target shape by removing layers, heads, and intermediate and hidden dimensions in an end-to-end manner, and (2) dynamic batch loading, which dynamically updates the composition of sampled data in each training batch based on varying losses across different domains.
  arXiv  Detail & Related papers  (2023-10-10T15:13:30Z)

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.