brittlewis12/gemma-2b-it-GGUF
Same weights, converted vs google/gemma-2b-it. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72
Same weights, converted vs google/gemma-2b-it. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72