My main goal is to merge the smartness of the base Instruct Nemo with the better prose from the different roleplaying fine-tunes. This is version v0.2, still to be tested. Not sure if it's better than v1.0. All credits and thanks go to Intervitens, Mistralai, and NeverSleep for providing amazing models used in the merge.
Mistral Instruct.
Lower Temperature of 0.35 recommended, although I had luck with Temperatures above one (1.0-1.2) if you crank up the Min P (0.01-0.1). Run with base DRY of 0.8/1.75/2/0 and you're good to go.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Model Stock merge method using F:\mergekit\mistralaiMistral-Nemo-Base-2407 as a base.
1models:
2 - model: F:\mergekit\NeverSleep_Lumimaid-v0.2-12B
3 - model: F:\mergekit\intervitens_mini-magnum-12b-v1.1
4 - model: F:\mergekit\mistralaiMistral-Nemo-Instruct-2407
5merge_method: model_stock
6base_model: F:\mergekit\mistralaiMistral-Nemo-Base-2407
7parameters:
8 filter_wise: false
9dtype: bfloat16
