namquangstudy/aaie-gft-full-fg-8k-dpo
Full fine-tune vs moinsaj/aaie-gft-full-fg-8k. Fine-tune: 100% of the weights changed, across 20 of 20 layers.
Tensors changed: Embeddings 1/1, Norms 41/41, MLP 60/60, Attention 80/80
Full fine-tune vs moinsaj/aaie-gft-full-fg-8k. Fine-tune: 100% of the weights changed, across 20 of 20 layers.
Tensors changed: Embeddings 1/1, Norms 41/41, MLP 60/60, Attention 80/80