newmindai/TurkEmbed4STS

Full fine-tune vs Alibaba-NLP/gte-multilingual-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 4/4, Attention 72/72, MLP 60/60

1 derivatives checked

• newmindai/TurkEmbed4Retrieval: Full fine-tune

On the Hub · Downloads on Model Pulse