mradermacher/GemMaroc-27b-it-GGUF
Quantization (fewer layers) vs AbderrahmanSkiredj1/GemMaroc-27b-it. mradermacher/GemMaroc-27b-it-GGUF matches part of AbderrahmanSkiredj1/GemMaroc-27b-it (808 of its 1247 tensors; the rest of AbderrahmanSkiredj1/GemMaroc-27b-it has no counterpart). On the shared part: mradermacher/GemMaroc-27b-it-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, Attention 0/248, MLP 0/186