microsoft/GUI-Actor-7B-Qwen2-VL
Full fine-tune vs Qwen/Qwen2-VL-7B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 155/187, MLP 215/216, Attention 324/324, Embeddings 1/1
Full fine-tune vs Qwen/Qwen2-VL-7B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 155/187, MLP 215/216, Attention 324/324, Embeddings 1/1