mradermacher/Napoleon-3.5-12B-GGUF

Same weights, converted vs baconnier/Napoleon-3.5-12B. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 30 new tensors.

Tensors changed: Norms 0/101, lm_head 0/1, Embeddings 0/1, MLP 0/120, Attention 0/40

On the Hub · Downloads on Model Pulse