Occamrazor

mpt-7b-storywriter-4bit-128g

OccamRazor

122

mpt-7b-storywriter-4bit-128g is a model designed to read and write fictional stories with super long context lengths. It was built by finetuning MPT-7B with a context length of 65k tokens on a filtered fiction subset of the books3 dataset. At inference time, thanks to ALiBi, mpt-7b-storywriter-4bit-128g can extrapolate even beyond 65k tokens. The maintainer OccamRazor demonstrates generations as long as 84k tokens on a single node of 8 A100-80GB GPUs in their blogpost. Model inputs and outputs mpt-7b-storywriter-4bit-128g is a text-to-text model that can be used to generate long-form fictional stories. It takes arbitrary text as input and outputs generated text. Inputs Arbitrary text prompt Outputs Continuation and elaboration of the input text in the style of a fictional story Capabilities mpt-7b-storywriter-4bit-128g excels at generating coherent, long-form fictional narratives. It can maintain context and plot coherence over extremely long text sequences, producing stories that can span tens of thousands of tokens. This makes it well-suited for applications that require the generation of lengthy, structured creative writing. What can I use it for? mpt-7b-storywriter-4bit-128g could be used to assist creative writers by generating story ideas, plot points, or even full narrative arcs that writers can then expand upon. It could also be used to create interactive fiction or text-based adventure games, where the model generates the narrative content dynamically based on user inputs. Additionally, the model's capabilities could be leveraged for educational purposes, such as helping students practice creative writing or analyze literary elements in fictional stories. Things to try One interesting aspect of mpt-7b-storywriter-4bit-128g is its ability to extrapolate beyond the 65k token context length it was trained on, thanks to the ALiBi technique. This means you can try feeding the model very long input texts and see how it continues the story, potentially generating coherent narratives that span tens of thousands of tokens. Experimenting with different prompts and genres could also yield interesting results and showcase the model's versatility in creative writing.

Read more