ThakiCloud/SKILLRET-Edge-109M-int3
Full fine-tune vs ThakiCloud/SKILLRET-Edge-109M. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 0/48, Attention 48/96, other 25/50
Full fine-tune vs ThakiCloud/SKILLRET-Edge-109M. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 0/48, Attention 48/96, other 25/50