OpenGVLab/InternVL3_5-14B-HF
Full fine-tune vs OpenGVLab/InternVL3_5-14B-MPO. Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 118/161, MLP 120/120, Attention 160/160, lm_head 1/1
Full fine-tune vs OpenGVLab/InternVL3_5-14B-MPO. Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 118/161, MLP 120/120, Attention 160/160, lm_head 1/1