GD-ML/DreamX-World-5B
Full fine-tune vs Wan-AI/Wan2.2-TI2V-5B. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Attention 480/480, Norms 180/180, MLP 120/120, other 35/35, Embeddings 10/10
Full fine-tune vs Wan-AI/Wan2.2-TI2V-5B. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Attention 480/480, Norms 180/180, MLP 120/120, other 35/35, Embeddings 10/10