KRLabsOrg/verbatim-rag-modern-bert-v2

Full fine-tune vs Alibaba-NLP/gte-reranker-modernbert-base. Fine-tune: 100% of the weights changed, across 22 of 22 layers.

Tensors changed: other 1/1, Norms 45/45, Embeddings 2/2, Attention 44/44, MLP 44/44

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

On the Hub · Downloads on Model Pulse