Pruning Large Language Models via Accuracy Predictor

• URL: http://arxiv.org/abs/2309.09507v2
• Date: Tue, 10 Oct 2023 03:13:38 GMT
• Title: Pruning Large Language Models via Accuracy Predictor
• Authors: Yupeng Ji, Yibo Cao, Jiucai Liu
• Abstract summary: Large language models (LLMs) containing tens of billions of parameters (or even more) have demonstrated impressive capabilities in various NLP tasks. We propose a novel pruning approach: firstly, a training set of a certain number of architecture-accuracy pairs is established, and then a non-neural model is trained as an accuracy predictor.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models(LLMs) containing tens of billions of parameters (or even more) have demonstrated impressive capabilities in various NLP tasks. However, substantial model size poses challenges to training, inference, and deployment so that it is necessary to compress the model. At present, most model compression for LLMs requires manual design of pruning features, which has problems such as complex optimization pipeline and difficulty in retaining the capabilities of certain parts of the model.Therefore, we propose a novel pruning approach: firstly, a training set of a certain number of architecture-accuracy pairs is established, and then a non-neural model is trained as an accuracy predictor. Using the accuracy predictor to further optimize the search space and search, the optimal model can be automatically selected. Experiments show that our proposed approach is effective and efficient. Compared with the baseline, the perplexity(PPL) on Wikitext2 and PTB dropped by 9.48% and 5,76% respectively, and the average accuracy of MMLU increased by 6.28%.

Related papers

• Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference [55.150117654242706]
  We show that model selection for computation-aware GPs trained on 1.8 million data points can be done within a few hours on a single GPU. As a result of this work, Gaussian processes can be trained on large-scale datasets without significantly compromising their ability to quantify uncertainty.
  arXiv  Detail & Related papers  (2024-11-01T21:11:48Z)
• Pruning Large Language Models with Semi-Structural Adaptive Sparse Training [17.381160429641316]
  We propose a pruning pipeline for semi-structured sparse models via retraining, termed Adaptive Sparse Trainer (AST) AST transforms dense models into sparse ones by applying decay to masked weights while allowing the model to adaptively select masks throughout the training process. Our work demonstrates the feasibility of deploying semi-structured sparse large language models and introduces a novel method for achieving highly compressed models.
  arXiv  Detail & Related papers  (2024-07-30T06:33:44Z)
• Crafting Efficient Fine-Tuning Strategies for Large Language Models [2.633490094119608]
  Fine-tuning large language models (LLMs) with as few as 200 samples can improve model accuracy from 70% to 88% in a product attribute extraction task. A bayesian hyperparameter optimization method, which evaluates models at 20% of total training time, correlates strongly with final model performance. This approach led to a 2% improvement in accuracy over baseline models when evaluated on an independent test set.
  arXiv  Detail & Related papers  (2024-07-18T21:36:00Z)
• Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs [54.05511925104712]
  We propose a simple, effective, and data-efficient method called Step-DPO. Step-DPO treats individual reasoning steps as units for preference optimization rather than evaluating answers holistically. Our findings demonstrate that as few as 10K preference data pairs and fewer than 500 Step-DPO training steps can yield a nearly 3% gain in accuracy on MATH for models with over 70B parameters.
  arXiv  Detail & Related papers  (2024-06-26T17:43:06Z)
• Fairer and More Accurate Tabular Models Through NAS [14.147928131445852]
  We propose using multi-objective Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) in the first application to the very challenging domain of tabular data. We show that models optimized solely for accuracy with NAS often fail to inherently address fairness concerns. We produce architectures that consistently dominate state-of-the-art bias mitigation methods either in fairness, accuracy or both.
  arXiv  Detail & Related papers  (2023-10-18T17:56:24Z)
• PruMUX: Augmenting Data Multiplexing with Model Compression [42.89593283051397]
  In this paper, we combine two such methods -- structured pruning and data multiplexing -- to compound the speedup gains obtained by either method. Our approach, PruMUX, obtains up to 7.5-29.5X throughput improvement over BERT-base model with accuracy threshold from 80% to 74%. We propose Auto-PruMUX, a meta-level model that can predict the high-performance parameters for pruning and multiplexing given a desired accuracy loss budget.
  arXiv  Detail & Related papers  (2023-05-24T04:22:38Z)
• Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time [69.7693300927423]
  We show that averaging the weights of multiple models fine-tuned with different hyper parameter configurations improves accuracy and robustness. We show that the model soup approach extends to multiple image classification and natural language processing tasks.
  arXiv  Detail & Related papers  (2022-03-10T17:03:49Z)
• Sparse MoEs meet Efficient Ensembles [49.313497379189315]
  We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs) We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
  arXiv  Detail & Related papers  (2021-10-07T11:58:35Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
  We argue for the use of neural generative models to characterize the worst-case distribution. This approach poses a number of implementation and optimization challenges. We find that the proposed approach yields models that are more robust than comparable baselines.
  arXiv  Detail & Related papers  (2021-03-18T14:26:26Z)

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.