OpenGVLab/InternVL3-14B-hf
Full fine-tune vs OpenGVLab/InternVL3-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 94/97, MLP 144/144, Attention 336/336, lm_head 1/1
Full fine-tune vs OpenGVLab/InternVL3-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 94/97, MLP 144/144, Attention 336/336, lm_head 1/1