This is a merge of pre-trained language models created using
mergekit.
This is my fifth model. The original model was created as a simple test of
Model Stock, thus the name (nepoticide=nephew, not as important nor direct). A broken tokenizer caused me to remerge the model. I also chose to use
TheDrummer/UnslopNemo-12B-v4, as TheDrummer stated that this model has more anti-gptism influence while taking a hit to intelligence, which should get balanced by the other models.
I do not know how this model holds up over long term context. Early testing showed stability and viable answers.
This model was merged using the
Model Stock merge method using
TheDrummer/UnslopNemo-12B-v4 as a base.
1models:
2 - model: MarinaraSpaghetti/NemoMix-Unleashed-12B
3 - model: inflatebot/MN-12B-Mag-Mell-R1
4 - model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
5 - model: TheDrummer/UnslopNemo-12B-v4
6base_model: TheDrummer/UnslopNemo-12B-v4
7merge_method: model_stock
8dtype: bfloat16
9chat_template: "chatml"
10tokenizer:
11 source: union
12
13