Meituan open-sources its 1.6-trillion-parameter large model, LongCat-2.5—training it on homegrown chips is awesome!
Did you know? Meituan recently open-sourced LongCat-2.5, an agent model with 1.6 trillion parameters, trained entirely on homegrown chips! It supports a context window of 1 million tokens. Impressive, right? #MeituanOpenSource# #AgentModel#
Did you know? Meituan recently open-sourced LongCat-2.5, an agent model with 1.6 trillion parameters, trained entirely on homegrown chips! It supports a context window of 1 million tokens. Impressive, right? #MeituanOpenSource# #AgentModel#