On April 10, Moonshot AI open source lightweight visual language model KIMi-VL and KIMi-VL-Thinking, the new model adopts MoE architecture, supports 128K context, and activates only about 3 billion parameters; Multimodal reasoning capability over 10 times the size of large models in multiple benchmarks.
Kimi open source multimodal model KIMI-VL, KIMi-VL-Thinking
On April 10, Moonshot AI open source lightweight visual language model KIMi-VL and KIMi-VL-Thinking, the new model adopts MoE architecture, supports 128K context, and activates only about 3 billion parameters; Multimodal reasoning capability over 10 times the size of large models in multiple benchmarks.