DatarrX/myX-Semantic
Full fine-tune vs sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/3, Attention 96/96, other 49/50
Full fine-tune vs sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/3, Attention 96/96, other 49/50