OpenGVLab/InternVL2_5-8B-MPO

Full fine-tune vs OpenGVLab/InternVL2_5-8B. Fine-tune: 95% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 160/160, Norms 76/161, MLP 195/198, Embeddings 4/5, other 1/49

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

On the Hub · Downloads on Model Pulse