OpenGVLab/HoVLE
Full fine-tune vs internlm/internlm2-chat-1_8b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 48/48, Norms 49/49, MLP 72/72
Full fine-tune vs internlm/internlm2-chat-1_8b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 48/48, Norms 49/49, MLP 72/72