OpenGVLab/InternVL3_5-241B-A28B-Flash

Full fine-tune vs OpenGVLab/InternVL3_5-241B-A28B. Fine-tune: 100% of the weights changed, across 94 of 94 layers.

Tensors changed: Norms 455/557, MLP 1770/1775, Attention 511/511, other 90/90, lm_head 1/1, Embeddings 4/5

On the Hub · Downloads on Model Pulse