OpenGVLab/InternVL3_5-8B-HF
Full fine-tune vs OpenGVLab/InternVL3_5-8B-MPO. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 113/145, MLP 108/108, Attention 144/144, lm_head 1/1
Full fine-tune vs OpenGVLab/InternVL3_5-8B-MPO. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 113/145, MLP 108/108, Attention 144/144, lm_head 1/1