mradermacher/NinjaMouse-3B-40L-danube-GGUF

Same weights, converted vs trollek/NinjaMouse-3B-40L-danube. Same weights stored in another dtype (BF16/F32 → F16/F32).

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

On the Hub · Downloads on Model Pulse