jenerallee78/Ministral-3-14B-abliterated-GGUF

Same weights, converted (fewer layers) vs jenerallee78/Ministral-3-14B-abliterated. jenerallee78/Ministral-3-14B-abliterated-GGUF matches part of jenerallee78/Ministral-3-14B-abliterated (363 of its 585 tensors; the rest of jenerallee78/Ministral-3-14B-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse