whybe-choi/kovre
Partial fine-tune vs Qwen/Qwen3-VL-Embedding-2B. Partial change: 85% of the weights changed (attention, embeddings, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 3/4, Norms 150/217, MLP 184/196, Attention 208/208
Partial fine-tune vs Qwen/Qwen3-VL-Embedding-2B. Partial change: 85% of the weights changed (attention, embeddings, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 3/4, Norms 150/217, MLP 184/196, Attention 208/208