BIOMEDICA/BMC-smolvlm1-256M
Full fine-tune vs HuggingFaceTB/SmolVLM-256M-Instruct. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: lm_head 1/1, other 1/1, Embeddings 4/4, Norms 22/111, MLP 132/138, Attention 208/216
Full fine-tune vs HuggingFaceTB/SmolVLM-256M-Instruct. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: lm_head 1/1, other 1/1, Embeddings 4/4, Norms 22/111, MLP 132/138, Attention 208/216