OpenGVLab/InternVL3_5-2B-Instruct

Full fine-tune vs OpenGVLab/InternVL3_5-2B-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

1 derivatives checked

• OpenGVLab/InternVL3_5-2B-MPO: Partial fine-tune

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse