mradermacher/HomePhi4_4B_FP16-GGUF
Same weights, converted vs TitleOS/HomePhi4_4B_FP16. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64
Same weights, converted vs TitleOS/HomePhi4_4B_FP16. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64