a-yakovenko/optical-flow-FreeFlow-L-TaTSKH-HQ
Full fine-tune vs a-yakovenko/optical-flow-FreeFlow-L-TaTSKH. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: Attention 384/384, MLP 192/192, Norms 324/324, other 72/72, Embeddings 4/4
2 derivatives checked
- a-yakovenko/optical-flow-FreeFlow-L-spring: Full fine-tune
- a-yakovenko/optical-flow-FreeFlow-L-sintel: Full fine-tune