mradermacher/CRePE-Mini-i1-GGUF
Quantization (fewer layers) vs SL-AI/CRePE-Mini. mradermacher/CRePE-Mini-i1-GGUF matches part of SL-AI/CRePE-Mini (530 of its 845 tensors; the rest of SL-AI/CRePE-Mini has no counterpart). On the shared part: mradermacher/CRePE-Mini-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 193 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/144, Attention 0/192