soob3123/Veiled-Calla-12B-gguf
Same weights, converted (fewer layers) vs soob3123/Veiled-Calla-12B. soob3123/Veiled-Calla-12B-gguf matches part of soob3123/Veiled-Calla-12B (626 of its 1065 tensors; the rest of soob3123/Veiled-Calla-12B has no counterpart). On the shared part: Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192