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

Currently, over a thousand LLMs exist that are multi-purpose and are capableof performing real world tasks, including Q&A, text summarization, contentgeneration, etc. However, accessibility, scale and reliability of free modelsprevents them from being widely deployed in everyday use cases. To address thefirst two issues of access and scale, organisations such as HuggingFace havecreated model repositories where users have uploaded model weights andquantized versions of models trained using different paradigms, as well asmodel cards describing their training process. While some models reportperformance on commonly used benchmarks, not all do, and interpreting the realworld impact of trading off performance on a benchmark for model deploymentcost, is unclear. Here, we show that a herd of open source models can match orexceed the performance of proprietary models via an intelligent router. We showthat a Herd of open source models is able to match the accuracy of ChatGPT,despite being composed of models that are effectively 2.5x smaller. We showthat in cases where GPT is not able to answer the query, Herd is able toidentify a model that can, at least 40% of the time.

Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer