Cobra91310/Ornith-1.5-35B-A3B-DFlash2-draft-GGUF

Same weights, converted vs jzinno/Ornith-1.5-35B-A3B-DFlash2. Same weights stored in another dtype (BF16 → F16/F32), plus 28 new tensors.

Tensors changed: other 0/1, Norms 0/25, MLP 0/18, Attention 0/24

On the Hub · Downloads on Model Pulse