bartowski/mlabonne_gemma-3-12b-it-abliterated-GGUF

Same weights, converted (fewer layers) vs mlabonne/gemma-3-12b-it-abliterated. bartowski/mlabonne_gemma-3-12b-it-abliterated-GGUF matches part of mlabonne/gemma-3-12b-it-abliterated (626 of its 1065 tensors; the rest of mlabonne/gemma-3-12b-it-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192

On the Hub · Downloads on Model Pulse