DevQuasar-7/katanemo.Arch-Function-7B-GGUF
Same weights, converted vs katanemo/Arch-Function-7B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1
Same weights, converted vs katanemo/Arch-Function-7B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1