hotchpotch/japanese-reranker-xsmall-v2

Full fine-tune vs cl-nagoya/ruri-v3-pt-30m. Fine-tune: 100% of the weights changed, across 10 of 10 layers.

Tensors changed: Embeddings 2/2, Norms 20/20, Attention 20/20, MLP 20/20

2 derivatives checked

• hotchpotch/open-provence-reranker-xsmall-v1: Full fine-tune
• masahiroid/japanese-reranker-xsmall-v2-mlx: Same weights, converted

On the Hub · Downloads on Model Pulse