The LLM Surgeon

• URL: http://arxiv.org/abs/2312.17244v2
• Date: Wed, 20 Mar 2024 20:21:58 GMT
• Title: The LLM Surgeon
• Authors: Tycho F. A. van der Ouderaa, Markus Nagel, Mart van Baalen, Yuki M. Asano, Tijmen Blankevoort,
• Abstract summary: We explore data-driven compression of existing pretrained models as an alternative to training smaller models from scratch. We provide a general framework for unstructured, semi-structured and structured pruning and improve upon weight updates to capture more correlations between weights. Our method can prune rows and columns from a range of OPT models and Llamav2-7B by 20%-30%, with a negligible loss in performance.
• Score: 33.90611088414982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art language models are becoming increasingly large in an effort to achieve the highest performance on large corpora of available textual data. However, the sheer size of the Transformer architectures makes it difficult to deploy models within computational, environmental or device-specific constraints. We explore data-driven compression of existing pretrained models as an alternative to training smaller models from scratch. To do so, we scale Kronecker-factored curvature approximations of the target loss landscape to large language models. In doing so, we can compute both the dynamic allocation of structures that can be removed as well as updates of remaining weights that account for the removal. We provide a general framework for unstructured, semi-structured and structured pruning and improve upon weight updates to capture more correlations between weights, while remaining computationally efficient. Experimentally, our method can prune rows and columns from a range of OPT models and Llamav2-7B by 20%-30%, with a negligible loss in performance, and achieve state-of-the-art results in unstructured and semi-structured pruning of large language models.

Related papers

• DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization [61.492590008258986]
  Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. We propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains.
  arXiv  Detail & Related papers  (2024-11-21T12:02:39Z)
• TRAWL: Tensor Reduced and Approximated Weights for Large Language Models [11.064868044313855]
  We introduce TRAWL (Tensor Reduced and Approximated Weights for Large Language Models), a technique that applies tensor decomposition across multiple weight matrices to effectively denoise LLMs by capturing global structural patterns. Our experiments show that TRAWL improves model performance by up to 16% over baseline models on benchmark datasets, without requiring additional data, training, or fine-tuning.
  arXiv  Detail & Related papers  (2024-06-25T04:01:32Z)
• LaCo: Large Language Model Pruning via Layer Collapse [56.92068213969036]
  Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion. Existing methods such as model quantization, knowledge distillation, and model pruning are constrained by various issues. We propose a concise layer-wise structured pruner called textitLayer Collapse (LaCo), in which rear model layers collapse into a prior layer.
  arXiv  Detail & Related papers  (2024-02-17T04:16:30Z)
• 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)
• Efficiently Robustify Pre-trained Models [18.392732966487582]
  robustness of large scale models towards real-world settings is still a less-explored topic. We first benchmark the performance of these models under different perturbations and datasets. We then discuss on how complete model fine-tuning based existing robustification schemes might not be a scalable option given very large scale networks.
  arXiv  Detail & Related papers  (2023-09-14T08:07:49Z)
• Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture [68.13678918660872]
  We design a more capable parameter-sharing architecture based on matrix product operator (MPO) MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts. Our architecture shares the central tensor across all layers for reducing the model size.
  arXiv  Detail & Related papers  (2023-03-27T02:34:09Z)
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures [57.46093180685175]
  We demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. We add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales.
  arXiv  Detail & Related papers  (2021-06-10T15:41:53Z)
• Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers [94.43313684188819]
  We study the impact of model size in this setting, focusing on Transformer models for NLP tasks that are limited by compute. We first show that even though smaller Transformer models execute faster per iteration, wider and deeper models converge in significantly fewer steps. This leads to an apparent trade-off between the training efficiency of large Transformer models and the inference efficiency of small Transformer models.
  arXiv  Detail & Related papers  (2020-02-26T21:17:13Z)
• Scaling Laws for Neural Language Models [14.472857826717613]
  We study scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training.
  arXiv  Detail & Related papers  (2020-01-23T03:59:20Z)

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.