1). DBRX – a new 132B parameter open LLM that outperforms all the established open-source models on common benchmarks like MMLU and GSM8K; DBRX was pretrained on 12T tokens (text and code) and uses a mixture-of-experts (MoE) architecture.
DBRX: New 132B Open-Source LLM Outperforms Benchmarks
By
–
