K2-Horizon MoVA: MLA + SeedLM Collection K2-Horizon-MoVA-36B-A4B with multi-head latent attention (TransMLA, 2.3x smaller KV cache) and SeedLM seed weights, vs oQe. • 10 items • Updated 42 minutes ago
K2-Horizon MoVA: MLA + SeedLM Collection K2-Horizon-MoVA-36B-A4B with multi-head latent attention (TransMLA, 2.3x smaller KV cache) and SeedLM seed weights, vs oQe. • 10 items • Updated 42 minutes ago
txgsync/K2-Horizon-MoVA-36B-A4B-NSLM-p4mx-q4v Text Generation • 19B • Updated about 3 hours ago • 805