teknovizier/minilm-tekla-attr-embed-v1
Full fine-tune vs sentence-transformers/all-MiniLM-L12-v2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/3, Attention 96/96, other 48/50
Full fine-tune vs sentence-transformers/all-MiniLM-L12-v2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/3, Attention 96/96, other 48/50