MaziyarPanahi/codegemma-7b-it-GGUF
Same weights, converted vs google/codegemma-7b-it. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112
Same weights, converted vs google/codegemma-7b-it. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112