Salesforce/SweRankEmbed-Small
Full fine-tune vs nomic-ai/CodeRankEmbed. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: other 2/2, Embeddings 2/2, Attention 24/24, MLP 36/36, Norms 48/48
Full fine-tune vs nomic-ai/CodeRankEmbed. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: other 2/2, Embeddings 2/2, Attention 24/24, MLP 36/36, Norms 48/48