FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4
Full fine-tune vs FastVideo/FastVideo-FastH3-8-Step-V2. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: Attention 12/12, Embeddings 6/6, Norms 148/179, other 50/50
Full fine-tune vs FastVideo/FastVideo-FastH3-8-Step-V2. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: Attention 12/12, Embeddings 6/6, Norms 148/179, other 50/50