vllm-sr/mmbert-embed-finance
Full fine-tune vs vllm-sr/mmbert-embed-32k-2d-matryoshka. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: Embeddings 2/2, Norms 44/44, Attention 44/44, MLP 44/44
Full fine-tune vs vllm-sr/mmbert-embed-32k-2d-matryoshka. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: Embeddings 2/2, Norms 44/44, Attention 44/44, MLP 44/44