ReTok: Replacing Tokenizer to Enhance Representation Efficiency in Large Language Model
- URL: http://arxiv.org/abs/2410.04335v1
- Date: Sun, 6 Oct 2024 03:01:07 GMT
- Title: ReTok: Replacing Tokenizer to Enhance Representation Efficiency in Large Language Model
- Authors: Shuhao Gu, Mengdi Zhao, Bowen Zhang, Liangdong Wang, Jijie Li, Guang Liu,
- Abstract summary: We propose a method to improve model representation and processing efficiency by replacing the tokenizers of large language models (LLMs)
Our method can maintain the performance of the model after replacing the tokenizer, while significantly improving the decoding speed for long texts.
- Score: 9.1108256816605
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Tokenizer is an essential component for large language models (LLMs), and a tokenizer with a high compression rate can improve the model's representation and processing efficiency. However, the tokenizer cannot ensure high compression rate in all scenarios, and an increase in the average input and output lengths will increases the training and inference costs of the model. Therefore, it is crucial to find ways to improve the model's efficiency with minimal cost while maintaining the model's performance. In this work, we propose a method to improve model representation and processing efficiency by replacing the tokenizers of LLMs. We propose replacing and reinitializing the parameters of the model's input and output layers with the parameters of the original model, and training these parameters while keeping other parameters fixed. We conducted experiments on different LLMs, and the results show that our method can maintain the performance of the model after replacing the tokenizer, while significantly improving the decoding speed for long texts.
Related papers
- Scalable Language Models with Posterior Inference of Latent Thought Vectors [52.63299874322121]
Latent-Thought Language Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.
LTMs possess additional scaling dimensions beyond traditional LLMs, yielding a structured design space.
LTMs significantly outperform conventional autoregressive models and discrete diffusion models in validation perplexity and zero-shot language modeling.
arXiv Detail & Related papers (2025-02-03T17:50:34Z) - Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models [10.517704202614091]
sparse Mixture-of-Experts (MoEs) allow scaling the number of parameters without proportionally increasing the FLOPs per example.
We investigate how varying the sparsity level, i.e., the fraction of inactive parameters, impacts model's performance during pretraining and downstream few-shot evaluation.
arXiv Detail & Related papers (2025-01-21T18:51:15Z) - Numerical Pruning for Efficient Autoregressive Models [87.56342118369123]
This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning.
Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and modules, respectively.
To verify the effectiveness of our method, we provide both theoretical support and extensive experiments.
arXiv Detail & Related papers (2024-12-17T01:09:23Z) - Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement [0.7558576228782637]
We propose a framework for efficient Source-Free Domain Adaptation (SFDA)
Our approach introduces an improved paradigm for source-model preparation and target-side adaptation.
We demonstrate that our framework is compatible with various SFDA methods and achieves significant computational efficiency.
arXiv Detail & Related papers (2024-10-03T02:12:03Z) - XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection [30.687511115573038]
tool is a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models.
tool can enhance model performance while decreasing the computation load at MoE layers by over 50% without sacrificing performance.
arXiv Detail & Related papers (2024-02-27T08:18:02Z) - E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [55.50908600818483]
Fine-tuning large-scale pretrained vision models for new tasks has become increasingly parameter-intensive.
We propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation.
Our approach outperforms several state-of-the-art baselines on two benchmarks.
arXiv Detail & Related papers (2023-07-25T19:03:21Z) - LegoNet: A Fast and Exact Unlearning Architecture [59.49058450583149]
Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model.
We present a novel network, namely textitLegoNet, which adopts the framework of fixed encoder + multiple adapters''
We show that LegoNet accomplishes fast and exact unlearning while maintaining acceptable performance, synthetically outperforming unlearning baselines.
arXiv Detail & Related papers (2022-10-28T09:53:05Z) - 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) - Efficient End-to-End Speech Recognition Using Performers in Conformers [74.71219757585841]
We propose to reduce the complexity of model architectures in addition to model sizes.
The proposed model yields competitive performance on the LibriSpeech corpus with 10 millions of parameters and linear complexity.
arXiv Detail & Related papers (2020-11-09T05:22:57Z) - Rethinking embedding coupling in pre-trained language models [46.11201932668366]
We re-evaluate the standard practice of sharing weights between input and output embeddings in pre-trained language models.
We show that decoupled embeddings provide increased modeling flexibility, allowing us to significantly improve the efficiency of parameter allocation.
We are able to train models that achieve strong performance on the XTREME benchmark without increasing the number of parameters at the fine-tuning stage.
arXiv Detail & Related papers (2020-10-24T07:43:00Z)
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.