OpenGVLab/InternVL3-78B-hf
Full fine-tune vs OpenGVLab/InternVL3-78B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, MLP 240/240, Attention 558/560, Norms 121/161, lm_head 1/1
Full fine-tune vs OpenGVLab/InternVL3-78B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, MLP 240/240, Attention 558/560, Norms 121/161, lm_head 1/1