This model is primarily focused on chat and roleplay without any alignment. As such, it may output content that can be considered "unsafe" or "harmful." Please use the model responsibly and to your best judgement.

Prompt Format

This model uses the Pygmalion-2/Metharme prompt format. The model has been trained on prompts using three different roles, which are denoted by the following tokens: <|system|>, <|user|> and <|model|>.

The <|system|> prompt can be used to inject out-of-channel information behind the scenes, while the <|user|> prompt should be used to indicate user input. The <|model|> token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.

The model does not need to be prompted in this manner and can instead be used as a pure text completions model. It was trained to understand both methods of prompting.

Example Usage

<|system|>A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.<|user|>Write a story of enormous length that incorporates the following tags: consensual, fantasy, adventure, magic, romance.<|model|>[The Huntress] "I told you, we don't kill them." The elf woman spoke with firm resolve, her bow held at the ready, arrows nocked and quiver full. Her companions, a dwarf armed with a great axe and a human bearing a long sword backed her up. They were surrounded by a forest filled with towering trees, lush vegetation, and sunlight filtering...

Norquinal/PetrolWriter-7B

PetrolWriter

Prompt Format

Example Usage

Norquinal/
PetrolWriter-7B