mradermacher/Apex-2-Base-GGUF
Same weights, converted vs YOON1v/Apex-2-Base. Same weights stored in another dtype (F32 → F16/F32), plus 96 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/32, Attention 0/128
Same weights, converted vs YOON1v/Apex-2-Base. Same weights stored in another dtype (F32 → F16/F32), plus 96 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/32, Attention 0/128