coder543/command-a-plus-05-2026-gguf

Same weights, converted vs CohereLabs/command-a-plus-05-2026-bf16. Same weights stored in another dtype (BF16 → BF16/F32), plus 96 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/128, Attention 0/128

On the Hub · Downloads on Model Pulse