Xiaojian9992024/Qwen2.5-GrimReaper-Instruct-32B-SLERP-Preview
Full fine-tune vs Kaoeiri/Qwenwify-32B-v4. Fine-tune: 99% of the weights changed, across 64 of 64 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 128/129, MLP 189/192, Attention 441/448