Fast and Effective Weight Update for Pruned Large Language Models
- URL: http://arxiv.org/abs/2401.02938v2
- Date: Mon, 22 Jul 2024 14:34:04 GMT
- Title: Fast and Effective Weight Update for Pruned Large Language Models
- Authors: Vladimír Boža,
- Abstract summary: Pruning large language models (LLMs) is a challenging task due to their enormous size.
Recent approaches have either ignored fine-tuning entirely, or attempted layer-wise weight updates.
We propose a fast and effective weight update algorithm for pruned layers based on the Alternating Direction Method of Multipliers.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Pruning large language models (LLMs) is a challenging task due to their enormous size. The primary difficulty is fine-tuning the model after pruning, which is needed to recover the lost performance caused by dropping weights. Recent approaches have either ignored fine-tuning entirely, focusing on efficient pruning criteria, or attempted layer-wise weight updates, preserving the behavior of each layer. However, even layer-wise weight updates can be costly for LLMs, and previous works have resorted to various approximations. In our paper, we propose a fast and effective weight update algorithm for pruned layers based on the Alternating Direction Method of Multipliers (ADMM). We further extend it with a simple gradual pruning mask selection and achieve state-of-the-art pruning performance across a wide range of LLMs. Code is available at https://github.com/fmfi-compbio/admm-pruning.
Related papers
- Reassessing Layer Pruning in LLMs: New Insights and Methods [24.394438652261982]
We show that a simple approach, i.e., pruning the final 25% of layers followed by fine-tuning the textttlm_head and the remaining last three layer, yields remarkably strong performance.
We release the optimal model weights on Hface, and the code is available on GitHub.
arXiv Detail & Related papers (2024-11-23T13:31:16Z) - Pruning Foundation Models for High Accuracy without Retraining [48.256389781305415]
It is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations.
Post-training pruning methods are proposed to prune LLMs in one-shot without retraining.
Our experiments demonstrate the superior performance of the proposed methods in comparison to SOTA baselines.
arXiv Detail & Related papers (2024-10-21T01:23:34Z) - Search for Efficient Large Language Models [52.98684997131108]
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research.
Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration.
Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
arXiv Detail & Related papers (2024-09-25T21:32:12Z) - LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models [7.496469228171892]
Large language models (LLMs) have grown significantly in scale, leading to a critical need for efficient model pruning techniques.
We present LLM-Barber (Block-Aware Rebuilder for Sparsity Mask in One-Shot), a novel one-shot pruning framework that rebuilds the sparsity mask of pruned models without any retraining or weight reconstruction.
Our experiments show that LLM-Barber can efficiently prune models with 7B to 13B parameters on a single A100 GPU in just 30 minutes, achieving state-of-the-art results in both perplexity and zero-shot performance across various language benchmarks
arXiv Detail & Related papers (2024-08-20T08:13:52Z) - 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) - SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models [53.638791265113625]
Sparsity-Preserved efficient fine-tuning method for large language models.
Code will be made available at https://github.com/Lucky-Lance/SPP.
arXiv Detail & Related papers (2024-05-25T04:55:27Z) - Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods [5.135352292810664]
We show that simple depth pruning can effectively compress large language models (LLMs)
Our pruning method boosts inference speeds, especially under memory-constrained conditions.
We hope this work can help build compact yet capable LLMs.
arXiv Detail & Related papers (2024-02-05T09:44:49Z) - A Simple and Effective Pruning Approach for Large Language Models [58.716255689941896]
Large Languages Models (LLMs) are natural candidates for network pruning methods.
Existing methods, however, require either retraining, or solving a weight reconstruction problem reliant on second-order information.
We introduce a novel, straightforward yet effective pruning method, termed Wanda (Pruning by Weights and activations), designed to induce sparsity in pretrained LLMs.
arXiv Detail & Related papers (2023-06-20T17:18:20Z) - AdamP: Slowing Down the Slowdown for Momentum Optimizers on
Scale-invariant Weights [53.8489656709356]
Normalization techniques are a boon for modern deep learning.
It is often overlooked, however, that the additional introduction of momentum results in a rapid reduction in effective step sizes for scale-invariant weights.
In this paper, we verify that the widely-adopted combination of the two ingredients lead to the premature decay of effective step sizes and sub-optimal model performances.
arXiv Detail & Related papers (2020-06-15T08:35:15Z)
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.