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

Harness the 𝓯𝓻𝓮𝓪𝓴𝔂 power of allura-org/Bigger-Body-12b, with the amazing intelligence of PocketDoc/Dans-PersonalityEngine-V1.3.0-12b

It's 𝓯𝓻𝓮𝓪𝓴𝔂, but it isn't hypersensitive to the greeting. It's intelligent, but filthy.

A Bigger Personality.

This is a likely NSFW-biased roleplaying model that was primarily merged to eliminate Bigger-Body's flaw of initial message sensitivity. Dans-PersonalityEngine will still heavily improve story-telling and roleplaying capability due to its smarts.

Hopefully either DanChat-2 or Mistral instruct format should work. Try DanChat-2 first.

Have fun, and let me know (in tasteful detail) how it goes!

After maining this model for a while, Bigger-Personality seems to act very closely/near identically to Dan's PersonalityEngine in writing prose and intelligence.

I have no 'feel' for Bigger-Body beyond that it mimics the initial message very closely, so I have no knowledge on what knowledge traits/prose quirks to look for.

Like Dan's, BP doesn't fall into repetitive comma splices ({{char}} slumps into the chair, sinking into the leather seating.) and demonstrates Dan's-level intelligence, writing, and improv ability.

It also has Dan's strong instruction adherence and neutral/little positivity bias.

Ultimately, the objective was to make a model that has an "internal" writing style to handle mediocre/no character cards, and this succeeded at that.

This model was merged using the NuSLERP merge method.

The following models were included in the merge:

The following YAML configuration was used to produce this model: