bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF
Same weights, converted (fewer layers) vs mlabonne/gemma-3-27b-it-abliterated. bartowski/mlabonne_gemma-3-27b-it-abliterated-GGUF matches part of mlabonne/gemma-3-27b-it-abliterated (808 of its 1247 tensors; the rest of mlabonne/gemma-3-27b-it-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248