mradermacher/MagpieLM-8B-GGUF
Same weights, converted vs win10/MagpieLM-8B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/123, MLP 0/183, Attention 0/244
Same weights, converted vs win10/MagpieLM-8B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/123, MLP 0/183, Attention 0/244