mradermacher/SeaPhi3-mini-GGUF
Same weights, converted vs SeacomSrl/SeaPhi3-mini. Same weights stored in another dtype (F16 → F16/F32), plus 2 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64, lm_head 0/1
Same weights, converted vs SeacomSrl/SeaPhi3-mini. Same weights stored in another dtype (F16 → F16/F32), plus 2 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64, lm_head 0/1