CAUTION: This model was finetuned on a corpus that includes adult content and may produce mature content without warning.

MN-12B-Tarsus

Is a full-weight finetune of mistralai/Mistral-Nemo-Instruct-2407

Which underwent several intermediate steps.

This finetune was made with chatting/roleplaying via SillyTavern in mind and thus all of the testing was done there, with the goals being to:

-Reduce shiver-slop

-Make the model more conversationally proactive

-Give it a more human-like output (i.e. less gratuitous purple prose)

-Reducing overall positivity bias

It still responds well to Mistral-Instruct formatting.

The results are imperfect and its assistant capabilities suffered somewhat as a result but in quick testing it definitely seems to have achieved all of the goals to varying degrees.

It sometimes fumbles with tokens in odd places so it's certainly not perfect. Possibly best used as merge-fodder.

Trained using qlora-pipe