bairongz/QianfanOCR
Full fine-tune vs OpenGVLab/InternVL3_5-4B-MPO. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 241/241, MLP 210/210, Attention 240/240, Embeddings 4/4, other 48/48
Full fine-tune vs OpenGVLab/InternVL3_5-4B-MPO. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 241/241, MLP 210/210, Attention 240/240, Embeddings 4/4, other 48/48