DreamGen Opus is a family of uncensored models fine-tuned for (steerable) story writing and the model also works great for chat / RP.
The DreamGen Opus V0 7B model is derived from mistralai/Mistral-7B-v0.1.
WARNING Quantized versions manifest significant performance degradation compared to the original:
You can try the Opus V0 70B (AWQ) model for free on dreamgen.com.
Prompting
Please see the official documentation for more detailed guide, including how to prompt the model for chat / RP.
The (collaborative / steerable) story writing task teaches the model to respect <setting> and <instruction> inserted into the prompt.
Example prompt:
<setting>
(Setting provides general overview of the story and characters)
This story is a twist on the traditional Little Red Riding Hood story.
In this variation, the Little Red Riding Hood and her grandma are secretely werevoles.
</setting>
(Previous part of the story, potentially empty)
<instruction>
(Setting tells the model what should happen in the next few sentences / paragraphs)
The Little Red Riding hood confronts The Big Bad Wolf, transforming into her wolf form.
</instruction>
Dataset
The fine-tuning dataset consisted of >1M tokens of collaborative writing task examples, each example being up to 4096 tokens. On top of that, >20M tokens of more general, but less instructed examples were included to help preserve generalization.
All prose in the dataset is from actual humans, not AI generated.
Community
Join the DreamGen community on Discord, or follow our X/Twitter account for new model releases and other news.
We will soon be releasing models with longer context window, as well as models specifically fine-tuned for character chat & roleplay.
