moonshotai/Kimi-Linear-48B-A3B-Instruct
Kimi-Linear is a 48B-parameter instruction-tuned MoE model (~3B activated) with a linear-attention variant supporting very long context (1M tokens).
Linear-attention MoE with 1M-token context on a single node
Kimi-Linear is a 48B-parameter instruction-tuned MoE model (~3B activated) with a linear-attention variant supporting very long context (1M tokens).
Linear-attention MoE with 1M-token context on a single node
View on HuggingFace
View on ModelScope