mradermacher/Ministral-3-8B-Instruct-2512-BF16-abliterated-GGUF
Same weights, converted (fewer layers) vs s3nh/Ministral-3-8B-Instruct-2512-BF16-abliterated. mradermacher/Ministral-3-8B-Instruct-2512-BF16-abliterated-GGUF matches part of s3nh/Ministral-3-8B-Instruct-2512-BF16-abliterated (309 of its 531 tensors; the rest of s3nh/Ministral-3-8B-Instruct-2512-BF16-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/136