vocaela/Vocaela-500M
Full fine-tune vs HuggingFaceTB/SmolVLM2-500M-Video-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, other 1/1, Embeddings 4/4, Norms 115/115, MLP 144/144, Attention 224/224
Full fine-tune vs HuggingFaceTB/SmolVLM2-500M-Video-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, other 1/1, Embeddings 4/4, Norms 115/115, MLP 144/144, Attention 224/224