Entrar
insight - Efficient Fine-Tuning of Large Language Models
Compressing Large Language Models Using a Linear Combination of Random Basis
NOLA, a novel reparameterization technique, enables efficient fine-tuning of large language models by decoupling the number of trainable parameters from the model architecture and the chosen rank, breaking the rank-one decomposition limit of existing methods like LoRA.
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning of Large Language Models
HydraLoRA, an asymmetric LoRA architecture, enhances the efficiency and performance of fine-tuning large language models by leveraging a shared matrix A and multiple distinct matrices B to capture both common and task-specific knowledge.
Birbal: An Efficient 7B Instruct-Model Fine-Tuned with Curated Datasets
Birbal, a Mistral-7B based model, achieved a 35% performance improvement through high-quality instruction curation.
Produtos
© 2024 by Linnk AI