microsoft/GUI-Actor-3B-Qwen2.5-VL
Full fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 90/138, MLP 304/304, Attention 380/380, Embeddings 1/1
Full fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 90/138, MLP 304/304, Attention 380/380, Embeddings 1/1