mradermacher/Dark-Hermes3-Llama3.2-3B-GGUF
Same weights, converted vs mrcuddle/Dark-Hermes3-Llama3.2-3B. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: lm_head 0/1, Norms 0/57, MLP 0/84, Attention 0/112
Same weights, converted vs mrcuddle/Dark-Hermes3-Llama3.2-3B. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: lm_head 0/1, Norms 0/57, MLP 0/84, Attention 0/112