alexxxmf/survaiv-embeddinggemma-300m
Partial fine-tune vs google/embeddinggemma-300m. Partial change: 34% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Embeddings 0/1, Norms 32/145, MLP 72/72, Attention 96/96
Partial fine-tune vs google/embeddinggemma-300m. Partial change: 34% of the weights changed (attention, mlp, norms), in 24 of 24 layers.
Tensors changed: Embeddings 0/1, Norms 32/145, MLP 72/72, Attention 96/96