OpenSciLM/OpenScholar_Reranker

Full fine-tune vs BAAI/bge-reranker-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: other 100/100, Embeddings 5/5, Norms 96/96, Attention 192/192

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

On the Hub · Downloads on Model Pulse