louisbrulenaudet/lemone-embed-pro
Partial fine-tune vs Alibaba-NLP/gte-multilingual-base. Partial change: 37% of the weights changed (attention, embeddings, mlp), in 12 of 12 layers.
Tensors changed: Embeddings 3/4, Attention 72/72, MLP 60/60
Partial fine-tune vs Alibaba-NLP/gte-multilingual-base. Partial change: 37% of the weights changed (attention, embeddings, mlp), in 12 of 12 layers.
Tensors changed: Embeddings 3/4, Attention 72/72, MLP 60/60