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 introduce SOLAR 10.7B, a large language model (LLM) with 10.7 billionparameters, demonstrating superior performance in various natural languageprocessing (NLP) tasks. Inspired by recent efforts to efficiently up-scaleLLMs, we present a method for scaling LLMs called depth up-scaling (DUS), whichencompasses depthwise scaling and continued pretraining. In contrast to otherLLM up-scaling methods that use mixture-of-experts, DUS does not requirecomplex changes to train and inference efficiently. We show experimentally thatDUS is simple yet effective in scaling up high-performance LLMs from smallones. Building on the DUS model, we additionally present SOLAR 10.7B-Instruct,a variant fine-tuned for instruction-following capabilities, surpassingMixtral-8x7B-Instruct. SOLAR 10.7B is publicly available under the Apache 2.0license, promoting broad access and application in the LLM field.

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling