lightonai/GTE-ModernColBERT-v1
Full fine-tune vs Alibaba-NLP/gte-modernbert-base. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: Embeddings 1/1, Norms 44/44, Attention 44/44, MLP 44/44
4 derivatives checked
- lightonai/Reason-ModernColBERT: Full fine-tune
- lightonai/Agent-ModernColBERT: Full fine-tune
- topk-io/Iso-ModernColBERT: Full fine-tune
- VAGOsolutions/SauerkrautLM-Multi-ModernColBERT: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.