<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
The Opus V1 extension is the addition of the text role, and the addition / modification of role names.
Pay attention to the following:
The text messages can (but don't have to have) names, names are used to indicate the "active" character during role-play.
There can be multiple subsequent message with a text role, especially if names are involved.
There can be multiple names attached to a message.
The format for names is names= {{name[0]}}; {{name[1]}}, beware of the spaces after names= and after the ;. This spacing leads to most natural tokenization for the names.
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
story writing
Here's how you can prompt the model for the following tasks
Input: A brief plot description and the desired number of chapters.
Output: A description for each chapter.
And more...
Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with min_p in the range [0.01, 0.1] and with temperature in the range [0.5, 1.5], depending on your preferences. A good starting point would be min_p=0.1; temperature=0.8.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
token count distribution
Running the model
The model is should be compatible with any software that supports the base model, but beware of the prompting (see above).
