tencent/HiLS-Attention-7B
Full fine-tune vs allenai/Olmo-3-1025-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Norms 129/129, Attention 128/128, lm_head 1/1
Full fine-tune vs allenai/Olmo-3-1025-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 96/96, Norms 129/129, Attention 128/128, lm_head 1/1