mradermacher/Phi-2-OmniMatrix-GGUF
Same weights, converted vs bunnycore/Phi-2-OmniMatrix. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/2, Embeddings 0/1, Norms 0/66, MLP 0/128, Attention 0/256
Same weights, converted vs bunnycore/Phi-2-OmniMatrix. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/2, Embeddings 0/1, Norms 0/66, MLP 0/128, Attention 0/256