gguf-org/docling-gguf
Same weights, converted vs ibm-granite/granite-docling-258M. Same weights stored in another dtype (BF16 → F16).
Tensors changed: other 0/1, Embeddings 0/4, Norms 0/111, MLP 0/138, Attention 0/216
Same weights, converted vs ibm-granite/granite-docling-258M. Same weights stored in another dtype (BF16 → F16).
Tensors changed: other 0/1, Embeddings 0/4, Norms 0/111, MLP 0/138, Attention 0/216