SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching

• URL: http://arxiv.org/abs/2410.06364v1
• Date: Tue, 8 Oct 2024 20:58:24 GMT
• Title: SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching
• Authors: Tianyi Zhang, Junda Su, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava,
• Abstract summary: "Two-tower" architecture is used for compressing pre-trained LLM parameters into compact representations and fine-tuning the additive full-precision adapter. We propose SpaLLM (Sketched Adapting of LLMs), a novel compressive adaptation approach for LLMs. We show that SpaLLM sketches pre-trained LLM weights into lookup tables and directly fine-tunes the values in these tables.
• Score: 32.4599581528901
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Compressive adaptation approaches, such as QLoRA, are widely popular alternatives for reducing memory requirements during fine-tuning of large language models (LLMs) while producing models capable of handling various downstream tasks. The key idea is to employ a "two-tower" architecture: compressing pre-trained LLM parameters into compact representations and fine-tuning the additive full-precision adapter, which typically has few tunable parameters in low-rank format. However, the strict algebraic assumptions, such as low-rank assumption, and the complexity of composing two-tower architectures are some of the known shortcomings, resulting in a poor accuracy-efficiency trade-off. In response to these known limitations, we propose SpaLLM (Sketched Parameter Adaptation of LLMs), a novel compressive adaptation approach for LLMs. This method is also the first to illustrate parameter-sharing compression methods for LLM fine-tuning, which, unlike QLoRA, are free from strict low-rank algebraic assumptions on adapters. Furthermore, our proposal unifies model compression and adaptation into a single, streamlined process, eliminating the need for two-tower architectures. SpaLLM sketches pre-trained LLM weights into lookup tables and directly fine-tunes the values in these tables. This approach simplifies LLMs' compressive adaptation workflow, potentially improves multi-user serving efficiency, and delivers significantly better accuracy for both natural language understanding and generation tasks. Moreover, by avoiding the "two-tower" architecture, our framework only requires one compressed matrix multiplication per layer during inference, demonstrating superior inference efficiency compared to previous methods.

Related papers

• Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
  Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
  arXiv  Detail & Related papers  (2024-10-25T17:07:13Z)
• SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs [2.7624021966289605]
  Large Language Models (LLMs) have revolutionized natural language understanding and generation tasks. LLMs suffer from high memory consumption and slow inference times due to their large parameter sizes. This paper introduces SLiM, a novel approach for compressing LLMs using a one-shot Quantized Sparse Plus Low-rank Approximation.
  arXiv  Detail & Related papers  (2024-10-12T18:36:07Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs [44.03692512352445]
  Column-Level Adaptive weight Quantization (CLAQ) is a novel and effective framework for Large Language Models (LLMs) quantization. In this paper, we present a novel and effective CLAQ framework by introducing three different types of adaptive strategies for LLM quantization. Experiments on various mainstream open source LLMs including LLaMA-1, LLaMA-2 and Yi demonstrate that our methods achieve the state-of-the-art results across different bit settings.
  arXiv  Detail & Related papers  (2024-05-27T14:49:39Z)
• Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization [40.15915011575071]
  Low-rank compression is a promising technique to reduce non-essential parameters in large language models. We conduct empirical research on the low-rank characteristics of large models. We propose a low-rank compression method suitable for large language models.
  arXiv  Detail & Related papers  (2024-05-17T08:27:12Z)
• BiLLM: Pushing the Limit of Post-Training Quantization for LLMs [53.31402059062365]
  BiLLM is a groundbreaking 1-bit post-training quantization scheme tailored for pretrained large language models. It achieves for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families.
  arXiv  Detail & Related papers  (2024-02-06T09:26:34Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization [27.79783067245817]
  Large language models (LLMs) face the challenges in fine-tuning and deployment due to their high memory demands and computational costs. This paper presents Efficient Adaptation and Quantization-aware (PEQA) - a simple yet effective method that combines the advantages of PEFT with quantized LLMs.
  arXiv  Detail & Related papers  (2023-05-23T15:20:01Z)

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.