mradermacher/gemma-2-baku-2b-it-GGUF

Same weights, converted vs rinna/gemma-2-baku-2b-it. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104

On the Hub · Downloads on Model Pulse