mradermacher/Oryza-Sirocco-3B-ARC-GGUF
Same weights, converted (fewer layers) vs DrRiceIO7/Oryza-Sirocco-3B-ARC. mradermacher/Oryza-Sirocco-3B-ARC-GGUF matches part of DrRiceIO7/Oryza-Sirocco-3B-ARC (236 of its 458 tensors; the rest of DrRiceIO7/Oryza-Sirocco-3B-ARC has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104