MarcGrumpyOlejak/VerwaltungsAnthologie_Disco_7B

Full fine-tune vs DiscoResearch/DiscoLM_German_7b_v1. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 93/96, Attention 124/128

1 derivatives checked

On the Hub · Downloads on Model Pulse