bisectgroup/BiCA-small
Partial fine-tune vs thenlper/gte-small. Partial change: 62% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 23/48, Attention 72/96, other 46/50
Partial fine-tune vs thenlper/gte-small. Partial change: 62% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 23/48, Attention 72/96, other 46/50