BrandeisPatrick/Ouro-2.6B-GGUF
Same weights, converted vs ByteDance/Ouro-2.6B. Same weights stored in another dtype (BF16 → F16/F32), plus 48 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192
Same weights, converted vs ByteDance/Ouro-2.6B. Same weights stored in another dtype (BF16 → F16/F32), plus 48 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192