ThakiCloud/SKILLRET-Edge-22M-int4
Full fine-tune vs ThakiCloud/SKILLRET-Edge-22M. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 3/5, Norms 0/24, Attention 24/48, other 13/26
Full fine-tune vs ThakiCloud/SKILLRET-Edge-22M. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 3/5, Norms 0/24, Attention 24/48, other 13/26