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

We present LongQLoRA, an efficient and effective method to extend contextlength of large language models with less training resources. LongQLoRAcombines the advantages of Position Interpolation, QLoRA and Shift ShortAttention of LongLoRA. With a single 32GB V100 GPU, LongQLoRA can extend thecontext length of LLaMA2 7B and 13B from 4096 to 8192 and even to 12k within1000 finetuning steps. LongQLoRA achieves competitive perplexity performance onPG19 and Proof-pile datasets, our model outperforms LongLoRA and is very closeto MPT-7B-8K within the evaluation context length of 8192. We collect and build39k long instruction data to extend context length of Vicuna-13B from 4096 to8192 and achieve good performance both in long and short context generationtask. We also do some ablation experiments to study the effect of LoRA rank,finetuning steps and attention patterns in inference.The model weights,training data and code are avaliable athttps://github.com/yangjianxin1/LongQLoRA.

LongQLoRA: Efficient and Effective Method to Extend Context Length of Large Language Models