mradermacher/Veritas-12B-GGUF
Quantization (fewer layers) vs soob3123/Veritas-12B. mradermacher/Veritas-12B-GGUF matches part of soob3123/Veritas-12B (626 of its 1065 tensors; the rest of soob3123/Veritas-12B has no counterpart). On the shared part: mradermacher/Veritas-12B-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192