OpenGVLab/InternVL3_5-38B-HF
Full fine-tune vs OpenGVLab/InternVL3_5-38B-MPO. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 188/257, MLP 192/192, Attention 256/256, lm_head 1/1
Full fine-tune vs OpenGVLab/InternVL3_5-38B-MPO. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 188/257, MLP 192/192, Attention 256/256, lm_head 1/1