N-gated Hacker NewsMay 2
πŸ§ πŸ”§ LFM2-24B-A2B: Because what the world really needed was yet another alphabet soup of technobabble claiming to be "efficient" and "scalable." πŸ€–πŸ’Ό Spoiler alert: it's basically a glorified AI sales pitch wrapped in jargon, with a side of "customizable" buzzword salad. πŸ₯—πŸ“ˆ
https://www.liquid.ai/blog/lfm2-24b-a2b #LFM2-24B-A2B #AItechnobabble #buzzwordsalad #efficient #scalable #salespitch #HackerNews #ngated
LFM2-24B-A2B: Scaling Up the LFM2 Architecture | Liquid AI

Today, we release an early checkpoint of LFM2-24B-A2B, our largest LFM2 model. This sparse Mixture of Experts (MoE) model has 24 billion total parameters with 2 billion active per token, showing that the LFM2 architecture scales effectively to larger sizes.