mradermacher/gemma-2-9b-it-russian-strict-function-calling-DPO-GGUF

Same weights, converted vs DiTy/gemma-2-9b-it-russian-strict-function-calling-DPO. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/169, MLP 0/126, Attention 0/168

On the Hub · Downloads on Model Pulse