This is a completely uncensored model that has been trained to excel at roleplaying and creative writing. It can utilize the full 131K context.
Prompt Format
The model uses the following prompt format:
__SYSTEM__: system message here
__USER__: user message here
__ASSISTANT__: assistant message here
The model is capable of multi-turn conversations. A system message is not required, however, performance can improve if detailed instructions are provided in a system message.
Important: the recommended default temperature for this model is 0.7. Setting the temperature to 1.0 can sometimes result in nonsensical output.
