DevQuasar-9/ModelSpace.GemmaX2-28-2B-Pretrain-GGUF
Same weights, converted vs ModelSpace/GemmaX2-28-2B-Pretrain. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104
Same weights, converted vs ModelSpace/GemmaX2-28-2B-Pretrain. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104