Alibaba-NLP/gte-reranker-modernbert-base
Full fine-tune vs answerdotai/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
5 derivatives checked
- KRLabsOrg/verbatim-rag-modern-bert-v2: Full fine-tune
- redis/langcache-reranker-v1-bce: Full fine-tune
- hotchpotch/open-provence-reranker-v1-gte-modernbert-base: Full fine-tune
- redis/langcache-reranker-v2-mnrl: Full fine-tune
- kasraahmadi/job-eval-modernbert: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.