New merge of NeMo based models, thankfully this time with ChatML format. My goal was to create a smart and universal roleplaying model that is stable on higher contexts. So far seems to be better than my best Nemomix attempts, especially on the 64k+ context I've been using. All credits and thanks go to the amazing Gryphe, MistralAI, Anthracite, Sao10K and ShuttleAI for their amazing models.

ChatML but Mistral Instruct should work too (theoretically).

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant
{response}<|im_end|>

I recommend running Temperature 1.0-1.2 with 0.1 Top A or 0.01-0.1 Min P, and with 0.8/1.75/2/0 DRY. Also works with lower Temperatures below 1.0. Nothing more needed.

You can use my exact settings from here (use the ones from the ChatML Base/Customized folder): https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main.

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

This model was merged using the della_linear merge method using F:\mergekit\mistralaiMistral-Nemo-Base-2407 as a base.

The following models were included in the merge:

The following YAML configuration was used to produce this model: