English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, the instruction-tuning of large language models is a crucial areaof research in the field of natural language processing. Due to resource andcost limitations, several researchers have employed parameter-efficient tuningtechniques, such as LoRA, for instruction tuning, and have obtained encouragingresults In comparison to full-parameter fine-tuning, LoRA-based tuningdemonstrates salient benefits in terms of training costs. In this study, weundertook experimental comparisons between full-parameter fine-tuning andLoRA-based tuning methods, utilizing LLaMA as the base model. The experimentalresults show that the selection of the foundational model, training datasetscale, learnable parameter quantity, and model training cost are all importantfactors. We hope that the experimental conclusions of this paper can provideinspiration for training large language models, especially in the field ofChinese, and help researchers find a better trade-off strategy between trainingcost and model performance. To facilitate the reproduction of the paper'sresults, the dataset, model and code will be released.

A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model