bartowski/Naphula_Goetia-26B-A4B-v1.7-GGUF

Same weights, converted vs Naphula/Goetia-26B-A4B-v1.7. Same weights stored in another dtype (BF16 → BF16/F32), plus 151 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/271, MLP 0/90, other 0/30, Attention 0/115

On the Hub · Downloads on Model Pulse