MC7ever/spark-darwin-17b-3way
Full fine-tune vs ZZRI/Feihua-n2-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 84/84
Full fine-tune vs ZZRI/Feihua-n2-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 84/84