darkbit1001/OpenYourMind-gemma-4-12B-it-abliterated-uncensored-EXL3-4.00bpw-HB6HQ

Same weights, converted vs OpenYourMind/gemma-4-12B-it-abliterated-uncensored. Same weights stored in another dtype (BF16 → I16/BF16), plus 1324 new tensors.

Tensors changed: Embeddings 0/10, Norms 0/289, other 0/48

On the Hub · Downloads on Model Pulse