bartowski/gemma-2-27b-chatml-GGUF
Same weights, converted vs IntervitensInc/gemma-2-27b-chatml. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Attention 0/184, Norms 0/185, MLP 0/138
Same weights, converted vs IntervitensInc/gemma-2-27b-chatml. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Attention 0/184, Norms 0/185, MLP 0/138