cuong1692001/Terminal-12k-bottom80
Full fine-tune vs cuong1692001/Terminal-complete-8k. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 135/145, MLP 108/108, Attention 144/144
Full fine-tune vs cuong1692001/Terminal-complete-8k. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 135/145, MLP 108/108, Attention 144/144