DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights

• URL: http://arxiv.org/abs/2501.18596v1
• Date: Thu, 30 Jan 2025 18:59:55 GMT
• Title: DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights
• Authors: Liana Mikaelyan, Ayyoob Imani, Mathew Salvaris, Parth Pathak, Mohsen Fayyaz,
• Abstract summary: We introduce DeltaLLM, a new post-training compression technique to reduce the memory footprint of LLMs. For training, we adopt the progressing module replacement method and show that the lightweight training of the low-rank modules is sufficient to achieve performance on par with LLMs of comparable sizes trained from scratch. Our method also outperforms compression techniques JointDrop, LaCo, ShortGPT and SliceGPT with the same number of parameters removed.
• Score: 11.047879241587315
• License:
• Abstract: We introduce DeltaLLM, a new post-training compression technique to reduce the memory footprint of LLMs. We propose an alternative way of structuring LLMs with weight sharing between layers in subsequent Transformer blocks, along with additional low-rank difference matrices between them. For training, we adopt the progressing module replacement method and show that the lightweight training of the low-rank modules with approximately 30M-40M tokens is sufficient to achieve performance on par with LLMs of comparable sizes trained from scratch. We release the resultant models, DeltaLLAMA and DeltaPHI, with a 12% parameter reduction, retaining 90% of the performance of the base Llama and Phi models on common knowledge and reasoning benchmarks. Our method also outperforms compression techniques JointDrop, LaCo, ShortGPT and SliceGPT with the same number of parameters removed. For example, DeltaPhi 2.9B with a 24% reduction achieves similar average zero-shot accuracies as recovery fine-tuned SlicedPhi 3.3B with a 12% reduction, despite being approximately 400M parameters smaller with no fine-tuning applied. This work provides new insights into LLM architecture design and compression methods when storage space is critical.

Related papers

• SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching [32.4599581528901]
  "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.
  arXiv  Detail & Related papers  (2024-10-08T20:58:24Z)
• From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients [86.40635601953446]
  We study the emergence of low-rank structures across different layers of Modern Large Language Models. We present Weight Low-Rank Projection (WeLore) that unifies weight compression and memory-efficient fine-tuning as ONE.
  arXiv  Detail & Related papers  (2024-07-15T21:05:20Z)
• Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging [14.123313596780726]
  We propose Manifold-Based Knowledge Alignment and Layer Merging Compression (MKA) MKA uses manifold learning and the Normalized Pairwise Information Bottleneck measure to merge similar layers, reducing model size while preserving essential performance. Our findings show that MKA not only preserves model performance but also achieves substantial compression ratios, outperforming traditional pruning methods.
  arXiv  Detail & Related papers  (2024-06-24T05:57:55Z)
• 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)
• 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)
• GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection [133.45193150403537]
  Training Large Language Models (LLMs) presents significant memory challenges due to the growing size of weights and GPU states. In this work, we propose Gradient Low-Rank Projection (GaLore) as a memory-efficient training strategy. Our 8-bit GaLore further reduces memory by up to 82.5% and total training memory by 63.3%, compared to a BF16 baseline.
  arXiv  Detail & Related papers  (2024-03-06T07:29:57Z)
• Scaling Sparse Fine-Tuning to Large Language Models [67.59697720719672]
  Large Language Models (LLMs) are difficult to fully fine-tune due to their sheer number of parameters. We propose SpIEL, a novel sparse finetuning method which maintains an array of parameter indices and the deltas of these parameters relative to their pretrained values. We show that SpIEL is superior to popular parameter-efficient fine-tuning methods like LoRA in terms of performance and comparable in terms of run time.
  arXiv  Detail & Related papers  (2024-01-29T18:43:49Z)
• LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression [16.901290551711476]
  We study the potential to compress Large Language Models (LLMs) for monolingual Code generation via Low Rank Decomposition (LoRD) We then use Low Rank Decomposition (LoRD) to compress StarCoder 16B to 13.2B parameter with no drop and to 12.3B with minimal drop in HumanEval Pass@1 score, in less than 10 minutes on a single A100.
  arXiv  Detail & Related papers  (2023-09-25T10:35:17Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)

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.