Omartificial-Intelligence-Space/GATE-AraBert-v1
Full fine-tune vs Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/50
1 derivatives checked
- NAMAA-Space/GATE-Reranker-V1: Full fine-tune
1 other repos hold byte-for-byte identical weight files.