Sto'Vo'Kor 12B
mistralai/Mistral-Nemo-Instruct-2407 fine-tuned on a private collection of ~30M tokens worth of instruct and multi-turn RP.
Note: this model is an experiment separate from the Unslop Initiative. You will probably get whispers and spine shivers with this model. I think it's pretty good anyway.
Instruct Format
Instruct format is V3-Tekken, the same as Mistral Nemo Instruct (except the chat template used won't freak out if your turns get mixed up, like tends to happen in ST. Thanks, fizz!)
<s>[INST]{System or user instructions}[/INST]{AI Response}</s>
During training, system turns were given as the first user turn in the conversation, separate from the user character's first turn. i.e., System as user -> AI turn (filler or first turn) -> User first turn
Recommended Samplers
Whatever you're used to for Nemo should work. For me this is stable with:
- temp 0.7
- min-p 0.03
- DRY 0.5/1.75/5/1024
- Downloads last month
- 33
Model tree for ToastyPigeon/Sto-vo-kor-12B
Base model
mistralai/Mistral-Nemo-Base-2407