calcuis/phi4
Same weights, converted vs microsoft/phi-4-gguf. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 160 new tensors.
Tensors changed: other 0/1, Norms 0/81, MLP 0/40, Attention 0/40, lm_head 0/1
Same weights, converted vs microsoft/phi-4-gguf. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 160 new tensors.
Tensors changed: other 0/1, Norms 0/81, MLP 0/40, Attention 0/40, lm_head 0/1