docling-project/SmolDocling-256M-preview-mlx-bf16

Same weights, repacked vs docling-project/SmolDocling-256M-preview. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: lm_head 0/1, other 0/1, Embeddings 0/3, Norms 0/111, MLP 0/138, Attention 0/216

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse