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