OpenGVLab/InternVL3_5-241B-A28B-HF
Full fine-tune vs OpenGVLab/InternVL3_5-241B-A28B-MPO. Fine-tune: 93% of the weights changed, across 94 of 94 layers.
Tensors changed: Norms 252/377, MLP 1556/1560, Attention 376/376, lm_head 0/1, Embeddings 0/1
Full fine-tune vs OpenGVLab/InternVL3_5-241B-A28B-MPO. Fine-tune: 93% of the weights changed, across 94 of 94 layers.
Tensors changed: Norms 252/377, MLP 1556/1560, Attention 376/376, lm_head 0/1, Embeddings 0/1