arianraje/mimo-7b-gdn-hybrid-1B-OPD
Full fine-tune vs XiaomiMiMo/MiMo-7B-RL-0530. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 73/73, MLP 108/108, Attention 63/63, lm_head 1/1
Full fine-tune vs XiaomiMiMo/MiMo-7B-RL-0530. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 73/73, MLP 108/108, Attention 63/63, lm_head 1/1