neulab/Pangea-7B-hf
Full fine-tune (fewer layers) vs Qwen/Qwen2-7B-Instruct. Qwen/Qwen2-7B-Instruct matches part of neulab/Pangea-7B-hf (337 of its 735 tensors; the rest of neulab/Pangea-7B-hf has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196