Papuguinho/gemmuguinho-636m-GGUF
Same weights, converted vs Papuguinho/gemmuguinho-636m. Same weights stored in another dtype (BF16 → F16/F32), plus 54 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/109, MLP 0/18, Attention 0/72
Same weights, converted vs Papuguinho/gemmuguinho-636m. Same weights stored in another dtype (BF16 → F16/F32), plus 54 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/109, MLP 0/18, Attention 0/72