Joesh1/onca-3.0-12b-gguf
Same weights, converted vs Joesh1/onca-3.0-12b. Same weights stored in another dtype (F16 → F16/F32), plus 49 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184
Same weights, converted vs Joesh1/onca-3.0-12b. Same weights stored in another dtype (F16 → F16/F32), plus 49 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184