相关论文: Sparse Upcycling: Inference Inefficient Finetuning

Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch.…

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling. We study an iso-parameter regime where inputs exhibit latent modular structure but are…

We study dense and mixture-of-experts (MoE) transformers in a tiny-scale pretraining regime under a shared LLaMA-style decoder training recipe. The sparse model replaces dense feed-forward blocks with Mixtral-style routed experts. Dense…

Mixture-of-Experts (MoE) represents an ensemble methodology that amalgamates predictions from several specialized sub-models (referred to as experts). This fusion is accomplished through a router mechanism, dynamically assigning weights to…

Machine learning models based on the aggregated outputs of submodels, either at the activation or prediction levels, often exhibit strong performance compared to individual models. We study the interplay of two popular classes of such…

Large Language Models (LLMs) have achieved remarkable performance on a wide range of specialized tasks, exhibiting strong problem-solving capabilities. However, training these models is prohibitively expensive, and they often lack…

We present Sparse Interpolated Mixture-of-Experts (SIMoE) instruction-tuning, an end-to-end algorithm designed to fine-tune a dense pre-trained Large Language Model (LLM) into a MoE-style model that possesses capabilities in multiple…

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…

Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to…

Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still…

Multilingual machine translation has attracted much attention recently due to its support of knowledge transfer among languages and the low cost of training and deployment compared with numerous bilingual models. A known challenge of…

Mixture of Experts (MoE) models with conditional execution of sparsely activated layers have enabled training models with a much larger number of parameters. As a result, these models have achieved significantly better quality on various…

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard…

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduce power consumption and computational footprint.…

Mixture-of-Experts (MoE) models deliver high quality at low training FLOPs, but this efficiency often vanishes at inference. We identify a double penalty that structurally disadvantages MoE architectures during decoding: first, expert…

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…

The goal of this paper is to improve (upcycle) an existing large language model without the prohibitive requirements of continued pre-training of the full-model. The idea is to split the pre-training data into semantically relevant groups…

Large-scale pre-training of deep models, followed by fine-tuning them, has become the cornerstone of natural language processing (NLP). The prevalence of data coupled with computational resources has led to large models with a considerable…