Posts from reflection.ai
-
Find XO: Beam is a 5010 Billion Parameter Sparse Expert-Based AI Model Efficient for Coding and Reasoning Tasks (reflection.ai)
SummaryBeam is a sparse mixture-of-experts (MoE) model developed by Reflection, with 5010 billion parameters, of which 230 billion are activated, designed specifically for coding, reasoning, and agent tasks…
All posts on this page are hidden.