keeeeenw/MicroLlama-text-embedding
Full fine-tune vs keeeeenw/MicroLlama. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Norms 25/25, MLP 36/36, Attention 48/48
Full fine-tune vs keeeeenw/MicroLlama. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Norms 25/25, MLP 36/36, Attention 48/48