Scaling Efficient LLMs

• URL: http://arxiv.org/abs/2402.14746v4
• Date: Mon, 22 Sep 2025 13:37:52 GMT
• Title: Scaling Efficient LLMs
• Authors: B. N. Kausik,
• Abstract summary: "AI scaling law" for transformers suggests that the number of parameters must scale linearly with the size of the data.<n>We propose recurrent transformers, combining the efficacy of transformers with the efficiency of recurrent networks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Trained LLMs in the transformer architecture are typically sparse in that most of the parameters are negligible, raising questions on efficiency. Furthermore, the so called "AI scaling law" for transformers suggests that the number of parameters must scale linearly with the size of the data. In response, we inquire into efficient LLMs, i.e. those with the fewest parameters that achieve the desired accuracy on a training corpus. Specifically, by comparing theoretical and empirical estimates of the Kullback-Liebler divergence, we derive a natural AI scaling law that the number of parameters in an efficient LLM scales as $D^{\gamma}$ where $D$ is the size of the training data and $ \gamma \in [0.44, 0.72]$, suggesting the existence of more efficient architectures. Against this backdrop, we propose recurrent transformers, combining the efficacy of transformers with the efficiency of recurrent networks, progressively applying a single transformer layer to a fixed-width sliding window across the input sequence. Recurrent transformers (a) run in linear time in the sequence length, (b) are memory-efficient and amenable to parallel processing in large batches, (c) learn to forget history for language tasks, or accumulate history for long range tasks like copy and selective copy, and (d) are amenable to curriculum training to overcome vanishing gradients. In our experiments, we find that recurrent transformers perform favorably on benchmark tests.

Related papers

• Reparameterized LLM Training via Orthogonal Equivalence Transformation [54.80172809738605]
  We present POET, a novel training algorithm that uses Orthogonal Equivalence Transformation to optimize neurons.<n>POET can stably optimize the objective function with improved generalization.<n>We develop efficient approximations that make POET flexible and scalable for training large-scale neural networks.
  arXiv  Detail & Related papers  (2025-06-09T17:59:34Z)
• The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws [51.608402959163925]
  We present the first systematic exploration of optimal sparse pre-training configurations for large language models. We find that initiating pruning at 25% of total training compute and concluding at 75% achieves near-optimal final evaluation loss. We propose a new scaling law that modifies the Chinchilla scaling law to use the average parameter count over pre-training.
  arXiv  Detail & Related papers  (2025-01-21T20:23:22Z)
• Optimizing Low-Resource Language Model Training: Comprehensive Analysis of Multi-Epoch, Multi-Lingual, and Two-Stage Approaches [3.809045695573932]
  Existing works adopt multi-epoch, multi-lingual, and two-stage training to utilize the limited target language corpus efficiently. We exhaustively explore training setups for low-resource language LLM, combining these three approaches. As the amount of target language corpus decreases, the optimal training approach shifts from monolingual single-stage training to multi-lingual two-stage training at a compute budget dependent threshold.
  arXiv  Detail & Related papers  (2024-10-16T07:45:56Z)
• Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent [26.764893400499354]
  We show that linear looped Transformers can implement multi-step gradient descent efficiently for in-context learning.<n>Our results demonstrate that as long as the input data has a constant condition number, $n = O(d)$, the linear looped Transformers can achieve a small error.
  arXiv  Detail & Related papers  (2024-10-15T04:44:23Z)
• Q-Sparse: All Large Language Models can be Fully Sparsely-Activated [93.45300714803429]
  We introduce Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs) Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. We also introduce Block Q-Sparse for batch training and inference.
  arXiv  Detail & Related papers  (2024-07-15T17:59:29Z)
• Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis [16.253898272659242]
  This study focuses on Transformer-based LLMs, specifically applying low-rank parametrization to feedforward networks (FFNs) Experiments on the large RefinedWeb dataset show that low-rank parametrization is both efficient (e.g., 2.6$times$ FFN speed-up with 32% parameters) and effective during training. Motivated by this finding, we develop the wide and structured networks surpassing the current medium-sized and large-sized Transformer in perplexity and throughput performance.
  arXiv  Detail & Related papers  (2024-07-13T10:08:55Z)
• EfficientQAT: Efficient Quantization-Aware Training for Large Language Models [50.525259103219256]
  quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss. We propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP)
  arXiv  Detail & Related papers  (2024-07-10T17:53:30Z)
• SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining [39.56934385513862]
  Training large language models (LLMs) from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank structures on weights for efficient fine-tuning in terms of parameters and memory. We propose to parameterize the weights as a sum of low-rank and sparse matrices for pretraining, which we call SLTrain.
  arXiv  Detail & Related papers  (2024-06-04T11:14:21Z)
• Can Large Language Models Play Games? A Case Study of A Self-Play Approach [61.15761840203145]
  Large Language Models (LLMs) harness extensive data from the Internet, storing a broad spectrum of prior knowledge. Monte-Carlo Tree Search (MCTS) is a search algorithm that provides reliable decision-making solutions. This work introduces an innovative approach that bolsters LLMs with MCTS self-play to efficiently resolve turn-based zero-sum games.
  arXiv  Detail & Related papers  (2024-03-08T19:16:29Z)
• BiLLM: Pushing the Limit of Post-Training Quantization for LLMs [53.31402059062365]
  BiLLM is a groundbreaking 1-bit post-training quantization scheme tailored for pretrained large language models. It achieves for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families.
  arXiv  Detail & Related papers  (2024-02-06T09:26:34Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [89.8764435351222]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• RWKV: Reinventing RNNs for the Transformer Era [54.716108899349614]
  We propose a novel model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers.
  arXiv  Detail & Related papers  (2023-05-22T13:57:41Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• CodeGen2: Lessons for Training LLMs on Programming and Natural Languages [116.74407069443895]
  We unify encoder and decoder-based models into a single prefix-LM. For learning methods, we explore the claim of a "free lunch" hypothesis. For data distributions, the effect of a mixture distribution and multi-epoch training of programming and natural languages on model performance is explored.
  arXiv  Detail & Related papers  (2023-05-03T17:55:25Z)
• $k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference [75.08572535009276]
  In-Context Learning (ICL) formulates target tasks as prompt completion conditioned on in-context demonstrations. $k$NN Prompting first queries LLM with training data for distributed representations, then predicts test instances by simply referring to nearest neighbors. It significantly outperforms state-of-the-art calibration-based methods under comparable few-shot scenario.
  arXiv  Detail & Related papers  (2023-03-24T06:16:29Z)
• Linearizing Transformer with Key-Value Memory Bank [54.83663647680612]
  We propose MemSizer, an approach to project the source sequence into lower dimension representation. MemSizer not only achieves the same linear time complexity but also enjoys efficient recurrent-style autoregressive generation. We demonstrate that MemSizer provides an improved tradeoff between efficiency and accuracy over the vanilla transformer.
  arXiv  Detail & Related papers  (2022-03-23T18:10:18Z)
• Block-Recurrent Transformers [49.07682696216708]
  We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence. Our recurrent cell operates on blocks of tokens rather than single tokens, and leverages parallel computation within a block in order to make efficient use of accelerator hardware.
  arXiv  Detail & Related papers  (2022-03-11T23:44:33Z)
• NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework [10.656788279434798]
  We propose a simple and efficient learning framework, TLM, that does not rely on large-scale pretraining. On eight classification datasets in four domains, TLM achieves results better than or similar to pretrained language models.
  arXiv  Detail & Related papers  (2021-11-07T17:13:59Z)
• Finetuning Pretrained Transformers into RNNs [81.72974646901136]
  Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. A linear-complexity recurrent variant has proven well suited for autoregressive generation. This work aims to convert a pretrained transformer into its efficient recurrent counterpart.
  arXiv  Detail & Related papers  (2021-03-24T10:50:43Z)
• Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search [84.94597821711808]
  We extend PoWER-BERT (Goyal et al., 2020) and propose Length-Adaptive Transformer that can be used for various inference scenarios after one-shot training. We conduct a multi-objective evolutionary search to find a length configuration that maximizes the accuracy and minimizes the efficiency metric under any given computational budget. We empirically verify the utility of the proposed approach by demonstrating the superior accuracy-efficiency trade-off under various setups.
  arXiv  Detail & Related papers  (2020-10-14T12:28:08Z)

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.