oopere/pruned40-gemma-2-2b
Same weights, converted vs google/gemma-2-2b. Same weights stored in another dtype (F32 → F16).
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 0/104
Same weights, converted vs google/gemma-2-2b. Same weights stored in another dtype (F32 → F16).
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 0/104