jinaai/jina-reranker-v3.5

Full fine-tune vs Qwen/Qwen3-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 113/113, MLP 84/84, Attention 112/112

1 derivatives checked

• jinaai/jina-reranker-v3.5-GGUF: Same weights, repacked (fewer layers)

On the Hub · Downloads on Model Pulse