OpenGVLab/InternVL3_5-2B-Flash
Full fine-tune vs OpenGVLab/InternVL3_5-2B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 5/5, Norms 201/209, MLP 186/186, Attention 208/208, other 48/48
Full fine-tune vs OpenGVLab/InternVL3_5-2B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 5/5, Norms 201/209, MLP 186/186, Attention 208/208, other 48/48