Jongbin-kr/exaone-7b-verireason-reproduced-1513-fullft-epoch4
Partial fine-tune vs LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct. Partial change: 89% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: Attention 128/128, Norms 36/65, MLP 96/96, Embeddings 0/1, lm_head 0/1