Phr00tyMix-v3 did increase creativity, but at the expense of some of its instruction following and coherency. This mix is intended to fix that, which should improve its storytelling and obediency. This model is still very creative, uncensored (when asked to be) and smart.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Model Stock merge method using
Phr00t/Phr00tyMix-v3-32B as a base.
1merge_method: model_stock
2base_model: Phr00t/Phr00tyMix-v3-32B
3dtype: bfloat16
4models:
5 - model: Delta-Vector/Archaeo-32B-KTO
6 - model: allura-org/Qwen2.5-32b-RP-Ink
7 - model: arcee-ai/Virtuoso-Medium-v2
8 - model: Phr00t/Phr00tyMix-v2-32B
9 - model: nicoboss/DeepSeek-R1-Distill-Qwen-32B-Uncensored
10tokenizer:
11 source: "Delta-Vector/Archaeo-32B-KTO"
12
