memset0/vsqa-preview-14b-v2
Full fine-tune vs Wan-AI/Wan2.1-T2V-14B-Diffusers. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 240/240, Attention 640/640, MLP 160/160, other 43/43, Embeddings 12/12
Full fine-tune vs Wan-AI/Wan2.1-T2V-14B-Diffusers. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 240/240, Attention 640/640, MLP 160/160, other 43/43, Embeddings 12/12