OpenGVLab/InternVL3_5-14B-Flash
Full fine-tune vs OpenGVLab/InternVL3_5-14B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Attention 256/256, Norms 250/257, MLP 222/222, other 48/48, Embeddings 5/5, lm_head 1/1
Full fine-tune vs OpenGVLab/InternVL3_5-14B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Attention 256/256, Norms 250/257, MLP 222/222, other 48/48, Embeddings 5/5, lm_head 1/1