I just had to make use of Wayfarer. So essentially I added it to Progenitor 1.1 (because I am already using Llama 3.3 Instruct as a base, I thought the nemotron base on Progenitor 1.1 would be better for the merge.) And I also put in a touch extra Llama Negative hopefully the attempt yields fruitful results.

This is a merge of pre-trained language models created using mergekit.

This model was merged using the Linear DELLA merge method using meta-llama/Llama-3.3-70B-Instruct as a base.

The following models were included in the merge:

The following YAML configuration was used to produce this model: