himanshu23099/bge_embedding_finetune_v2

Full fine-tune vs BAAI/bge-small-en-v1.5. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/50

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse