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 the Bittensor Language Model, called "BTLM-3B-8K", a newstate-of-the-art 3 billion parameter open-source language model. BTLM-3B-8K wastrained on 627B tokens from the SlimPajama dataset with a mixture of 2,048 and8,192 context lengths. BTLM-3B-8K outperforms all existing 3B parameter modelsby 2-5.5% across downstream tasks. BTLM-3B-8K is even competitive with some 7Bparameter models. Additionally, BTLM-3B-8K provides excellent long contextperformance, outperforming MPT-7B-8K and XGen-7B-8K on tasks up to 8,192context length. We trained the model on a cleaned and deduplicated SlimPajamadataset; aggressively tuned the \textmu P hyperparameters and schedule; usedALiBi position embeddings; and adopted the SwiGLU nonlinearity.  On Hugging Face, the most popular models have 7B parameters, indicating thatusers prefer the quality-size ratio of 7B models. Compacting the 7B parametermodel to one with 3B parameters, with little performance impact, is animportant milestone. BTLM-3B-8K needs only 3GB of memory with 4-bit precisionand takes 2.5x less inference compute than 7B models, helping to open up accessto a powerful language model on mobile and edge devices. BTLM-3B-8K isavailable under an Apache 2.0 license on Hugging Face:https://huggingface.co/cerebras/btlm-3b-8k-base.

BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model