Mostly quanting this because I want to see how it performs.
The result of this merge is in my opinion a more vibrant and less generic sonnet inspired prose, it's able to be gentle and harsh where asked.
I've personally been trying to get a more spice while also compensating for the Magnum-v2.5 having the issue on my end that it simply won't stop yapping.
Initial feedback shows that the model has a tendency to promote flirting. If this becomes too much try to steer the model with a system prompt to focus on SFW and on-flirty interactions.
Both Mistral and ChatML should work though I had better results with ChatML:
ChatML Example:
1"""<|im_start|>user
2Hi there!<|im_end|>
3<|im_start|>assistant
4Nice to meet you!<|im_end|>
5<|im_start|>user
6Can I ask a question?<|im_end|>
7<|im_start|>assistant
8"""
This model was merged using the
DARE TIES merge method using
Sao10K/MN-12B-Lyra-v3 as a base.
Special thanks to the SillyTilly and myself for helping me find the energy to finish this.
