mradermacher/Shark-1-Ogno-9b-passthrough-GGUF

Same weights, converted vs powermove72/Shark-1-Ogno-9b-passthrough. Same weights stored in another dtype (F16 → F16/F32).

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

On the Hub · Downloads on Model Pulse