fpc/bge-micro-smiles
Partial fine-tune vs TaylorAI/bge-micro. Partial change: 32% of the weights changed (attention, embeddings, norms, other), in 3 of 3 layers.
Tensors changed: Embeddings 4/5, Norms 12/12, Attention 24/24, other 12/14
Partial fine-tune vs TaylorAI/bge-micro. Partial change: 32% of the weights changed (attention, embeddings, norms, other), in 3 of 3 layers.
Tensors changed: Embeddings 4/5, Norms 12/12, Attention 24/24, other 12/14