322 citations · 592 across the 17 of their papers we have counts for
3 papers · 1 filter
Mixtral of Experts
Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux +23
We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model. Mixtral has the same architecture as Mistral 7B, with the difference that each layer is composed of 8…
Training Transformers Together
Alexander Borzunov, Max Ryabinin, Tim Dettmers +5
The infrastructure necessary for training state-of-the-art models is becoming overly expensive, which makes training such models affordable only to large corporations and instituti…
Distributed Deep Learning in Open Collaborations
Michael Diskin, Alexey Bukhtiyarov, Max Ryabinin +13
Modern deep learning applications require increasingly more compute to train state-of-the-art models. To address this demand, large corporations and institutions use dedicated High…