mradermacher/kisoku-3b-sft-GGUF
Same weights, converted vs 0arch-io/kisoku-3b-sft. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112
Same weights, converted vs 0arch-io/kisoku-3b-sft. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112