mradermacher/gemma-3b-it-expanded-GGUF
Same weights, converted vs arcee-ai/gemma-3b-it-expanded. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96
Same weights, converted vs arcee-ai/gemma-3b-it-expanded. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96