Trappu/Picaro-Apparatus-0.8-24b

Full fine-tune vs OddTheGreat/Apparatus_24B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 5/81, MLP 120/120, Attention 160/160

1 derivatives checked

On the Hub · Downloads on Model Pulse