§ feed · storyline
ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math
ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math
This storyline groups 1 article from 1 source. The originating feed didn’t ship an excerpt — open any link below to read the piece.
§ sources1 publication · timeline below