mradermacher/Mira-v1.13-27B-custom-heretic-ties-GGUF
Quantization (fewer layers) vs Lambent/Mira-v1.13-27B-custom-heretic-ties. mradermacher/Mira-v1.13-27B-custom-heretic-ties-GGUF matches part of Lambent/Mira-v1.13-27B-custom-heretic-ties (808 of its 1247 tensors; the rest of Lambent/Mira-v1.13-27B-custom-heretic-ties has no counterpart). On the shared part: mradermacher/Mira-v1.13-27B-custom-heretic-ties-GGUF is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 435 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248