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

An RP merge with a focus on:
- model intelligence
- removing positive bias
- creativity

This model was merged using the sce merge method using deepseek-r1-distill-llama-70b as a base.

Note: forcing the llama3.3 chat template can sometimes yield better results. The deepseek chat template is the default provided in config.

The following models were included in the merge:

The following YAML configuration was used to produce this model: