With the rise of the fine-tuned-pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information.

With the rise of the fine-tuned-pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information.

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary 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 (e.g., WizardMath for math problems). Motivated by the long-tail distribution of singular values in the delta weights, we propose a delta quantization approach using mixed-precision. This method employs higher-bit representation for singular vectors corresponding to larger singular values. We evaluate our approach on various fine-tuned LLMs, including math LLMs, code LLMs, chat LLMs, and even VLMs. Experimental results demonstrate that our approach performs comparably to full fine-tuned LLMs, surpassing both low-rank and low-bit baselines by a considerable margin. Additionally, we show that our method is compatible with various backbone LLMs, such as Llama-2, Llama-3, and Mistral, highlighting its generalizability.

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 (e.g., WizardMath for math problems).

With the rise of the fine-tuned-pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information. (2) Distribution-Aware Compression applies uniform quantization and then groups parameters by value, followed by group-wise pruning, to better preserve intra-layer distribution. (3) Trace-Norm-Guided Rescaling uses the trace norm of delta weights to estimate a global rescaling factor, improving model stability under higher compression. Extensive experiments across (a) large language models (fine-tuned on LLaMA-2 7B and 13B) with up to 50x compression, (b) general NLP models (RoBERTa-base, T5-base) with up to 224x compression, (c) vision models (ViT-B/32, ViT-L/14) with up to 132x compression, and (d) multi-modal models (BEiT-3) with 18x compression, demonstrate that UltraDelta consistently outperforms existing methods, especially under ultra-high compression. Code is available at https://github.com/xiaohuiwang000/UltraDelta.

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, like multi-tenant serving, a large number of LLMs finetuned from the same base model are deployed to meet complex requirements for users. Recent works explore delta-compression approaches to quantize and compress the delta weights between the customized LLM and the corresponding base model. However, they exhibit inadequate performance at high compression ratios due to their empirical nature. In this work, we introduce DeltaMix, an adaptive mixed-precision delta-compression framework designed to minimize quantization error in the singular value decomposition (SVD) space without imposing additional assumptions. DeltaMix provides a theoretical justification for the necessity of mixed-precision compression and presents a practical quantization solution that involves solving a 0/1 linear integer programming problem alongside a reconstruction target correction method. Experimental results across multiple models and benchmarks illustrate that DeltaMix consistently outperforms all baseline methods. Notably, on tasks such as AIME2024 and GQA, DeltaMix exceeds the performance of the best baseline, Delta-CoMe, by 22.3\% and 6.1\% for 7B parameter models, respectively.

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary 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 (e.g., WizardMath for math problems). Motivated by the long-tail distribution of singular values in the delta weights, we propose a delta quantization approach using mixed-precision.

Upcycled Mixture-of-Experts (MoE) models have shown great potential in various tasks by converting the original Feed-Forward Network (FFN) layers in pre-trained dense models into MoE layers. However, these models still suffer from significant parameter inefficiency due to the introduction of multiple experts. In this work, we propose a novel DeRS (Decompose, Replace, and Synthesis) paradigm to overcome this shortcoming, which is motivated by our observations about the unique redundancy mechanisms of upcycled MoE experts. Specifically, DeRS decomposes the experts into one expert-shared base weight and multiple expert-specific delta weights, and subsequently represents these delta weights in lightweight forms. Our proposed DeRS paradigm can be applied to enhance parameter efficiency in two different scenarios, including: 1) DeRS Compression for inference stage, using sparsification or quantization to compress vanilla upcycled MoE models; and 2) DeRS Upcycling for training stage, employing lightweight sparse or low-rank matrixes to efficiently upcycle dense models into MoE models. Extensive experiments across three different tasks show that the proposed methods can achieve extreme parameter efficiency while maintaining the performance for both training and compression of upcycled MoE models.

Mixture-of-Experts (MoE) architectures in large language models (LLMs) achieve exceptional performance, but face prohibitive storage and memory requirements. To address these challenges, we present $D^2$-MoE, a new delta decompression compressor for reducing the parameters of MoE LLMs. Based on observations of expert diversity, we decompose their weights into a shared base weight and unique delta weights. Specifically, our method first merges each expert's weight into the base weight using the Fisher information matrix to capture shared components. Then, we compress delta weights through Singular Value Decomposition (SVD) by exploiting their low-rank properties. Finally, we introduce a semi-dynamical structured pruning strategy for the base weights, combining static and dynamic redundancy analysis to achieve further parameter reduction while maintaining input adaptivity. In this way, our $D^2$-MoE successfully compact MoE LLMs to high compression ratios without additional training. Extensive experiments highlight the superiority of our approach, with over 13% performance gains than other compressors on Mixtral|Phi-3.5|DeepSeek|Qwen2 MoE LLMs at 40$\sim$60% compression rates. Codes are available in https://github.com/lliai/D2MoE.