mradermacher/supergemma4-e4b-abliterated-GGUF

Same weights, converted vs Jiunsong/supergemma4-e4b-abliterated. Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168

On the Hub · Downloads on Model Pulse