Virtue-AI-HUB/SafeWatch-8B
Full fine-tune vs OpenGVLab/InternVL2-8B. Fine-tune: 95% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 160/160, Norms 75/161, MLP 194/198, Embeddings 4/5, other 1/49
Full fine-tune vs OpenGVLab/InternVL2-8B. Fine-tune: 95% of the weights changed, across 32 of 32 layers.
Tensors changed: Attention 160/160, Norms 75/161, MLP 194/198, Embeddings 4/5, other 1/49