Get the latest tech news
Apple accelerates AI efforts: Here's what its new models can do
Meta, Google, and Mistral, watch out - you've got 7 billion parameters of competition and counting.
When tested on the Massive Multitask Language Understanding (MMLU) benchmark against popular models around the same size, DCLM-Baseline-7B performed competitively, even outperforming Mistral 7B, as seen below. Many are commending Apple for this approach as it allows other researchers and developers to build on the models and further grow advancements in the space. In addition to releasing DCLM-Baseline-7B, model weights, training code, and dataset, Apple also included a powerful 1.4 billion parameter version in the package.
Or read this on ZDNet
