CNWPlayer/Vega-SupraNeo-4M-Tetris-Verbose
Full fine-tune vs SupraLabs/SupraNeo-4M. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 36/36, Attention 48/48
Full fine-tune vs SupraLabs/SupraNeo-4M. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 36/36, Attention 48/48