Related papers: LoRAQuant: Mixed-Precision Quantization of LoRA to…

In recent years, pretrained large language models have demonstrated outstanding performance across various natural language processing tasks. However, full-parameter fine-tuning methods require adjusting all model parameters, leading to…

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory…

State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…

Fine-tuning Large Language Models (LLMs) and storing them for each downstream task or domain is impractical because of the massive model size (e.g., 350GB in GPT-3). Current literature, such as LoRA, showcases the potential of low-rank…

Parameter-Efficient Fine-Tuning (PEFT), particularly Low-Rank Adaptation (LoRA), has become a standard approach for adapting Large Language Models (LLMs) under limited compute. However, in continual settings where models are updated…

As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization methods, such as GPTQ, have made progress in achieving…

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrating LLM training and…

The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost during inference.…

It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based Adaptive Mixed-Precision Model Quantization (LCPAQ), which…

Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models, enabling large libraries of LoRAs, each for a specific task or domain. Efficiently selecting the correct LoRA adapter…

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…

Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, considering the practical constraints of computational and storage costs. Low-rank adaptation (LoRA) is a…

The efficient compression of large language models (LLMs) has become increasingly popular. However, recovering the performance of compressed LLMs remains a major challenge. The current practice in LLM compression entails the implementation…

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely influenced by the allocation of ranks and scaling factors, as well as initialization.…

Low-rank adaptation (LoRA) has become the default approach to fine-tune large language models (LLMs) due to its significant reduction in trainable parameters. However, trainable parameter demand for LoRA increases with increasing model…

Low-Rank Adaptation (LoRA) is a widely used finetuning method for large models. Its small memory footprint allows practitioners to adapt large models to specific tasks at a fraction of the cost of full finetuning. Different modifications…

Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning. However, significant challenges remain: (1) Simply increasing the rank size of LoRA does not effectively capture high-rank information, which leads…

This work presents a novel, fully Riemannian framework for Low-Rank Adaptation (LoRA) that geometrically treats low-rank adapters by optimizing them directly on the fixed-rank manifold. This formulation eliminates the parametrization…

Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between…

Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same…