jinaai/jina-reranker-m0
Full fine-tune vs Qwen/Qwen2-VL-2B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 2/2, Norms 187/187, MLP 216/216, Attention 324/324
1 derivatives checked
- jinaai/jina-reranker-m0-GGUF: Same weights, converted (fewer layers)
2 other repos hold byte-for-byte identical weight files.