vonjack/hrm-text-code-tools-sft
Full fine-tune vs sapientinc/HRM-Text-1B. Fine-tune: 91% of the weights changed, across 16 of 16 layers.
Tensors changed: lm_head 1/1, Attention 64/64, MLP 64/64, Embeddings 0/1, other 0/1
Full fine-tune vs sapientinc/HRM-Text-1B. Fine-tune: 91% of the weights changed, across 16 of 16 layers.
Tensors changed: lm_head 1/1, Attention 64/64, MLP 64/64, Embeddings 0/1, other 0/1