vidore/ColSmolVLM-Instruct-256M-base
Same weights, repacked vs HuggingFaceTB/SmolVLM-256M-Instruct. Same weights in different files (re-saved, re-sharded or new metadata), plus 2 new tensors.
Tensors changed: other 0/1, Embeddings 0/4, Norms 0/111, MLP 0/138, Attention 0/216
1 derivatives checked
- vidore/colSmol-256M: Adapter