Based on preliminary tests, I'm quite happy with the results. Very original responses and basically no alignment issues.
In my experience, it works well with ChatML, Alpaca, and likely other instruction sets - you can chat, or ask it to develop a story.
This model is intended for fictional storytelling and role-playing, and may not be intended for all audiences.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the passthrough merge method.
1slices:
2 - sources:
3 - model: ABX-AI/Cerebral-Infinity-7B
4 layer_range: [0, 20]
5 - sources:
6 - model: ABX-AI/Starfinite-Laymons-7B
7 layer_range: [12, 32]
8merge_method: passthrough
9dtype: float16
10