rsl-ai/octen-embedding-0.6-finetuned
Partial fine-tune vs Octen/Octen-Embedding-0.6B. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 73/113, MLP 84/84, Attention 112/112
Partial fine-tune vs Octen/Octen-Embedding-0.6B. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 73/113, MLP 84/84, Attention 112/112