The article presents LoraRetriever, a new framework that adaptively retrieves and composes multiple Low-Rank Adaptations (LoRAs) according to the input prompts in large language models (LLMs). It aims to enhance…
Continue readingThe article discusses the effectiveness of Parameter-Efficient Fine-Tuning (PEFT) in speech processing, with a particular focus on the optimal placement of PEFT methods, their merging strategies, and the use of…
Continue readingThe paper introduces CoLLiE, a library that assists in the collaborative training of large language models. It uses 3D parallelism, parameter-efficient fine-tuning (PEFT) methods, and a range of optimizers like…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
