hbriegel/AssistiveRecGraniteSmall
Full fine-tune vs ibm-granite/granite-embedding-125m-english. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/50
Full fine-tune vs ibm-granite/granite-embedding-125m-english. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/50