whoashish115/Moonfrost-777M-Instruct-v2
Full fine-tune vs whoashish115/Moonfrost-777M. Fine-tune: 100% of the weights changed, across 14 of 14 layers.
Tensors changed: other 0/2, Attention 70/70, Norms 57/57, MLP 94/94, Embeddings 1/1
Full fine-tune vs whoashish115/Moonfrost-777M. Fine-tune: 100% of the weights changed, across 14 of 14 layers.
Tensors changed: other 0/2, Attention 70/70, Norms 57/57, MLP 94/94, Embeddings 1/1