mradermacher/Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated-GGUF
Same weights, converted (fewer layers) vs 3MPER0RR/Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated. mradermacher/Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated-GGUF matches part of 3MPER0RR/Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated (236 of its 458 tensors; the rest of 3MPER0RR/Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104