This model is the experimental merge between
Verdict-8x7B and
Mixtral-Instruct-ITR-DADA-8x7B as outlined in the ITR-DADA model card.
It is a little less stable than the original Verdict but also much more creative. It still uses the [INST]do a thing[/INST] formatting.