Text Generation
GGUF
English
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
full precision
float 32
ultra quality
swearing
extreme swearing
rp
graphic horror
horror
nsfw
llama3
Not-For-All-Audiences
mergekit
Inference Endpoints
conversational
metadata
license: apache-2.0
language:
- en
tags:
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- fiction writing
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prosing
- vivid writing
- fiction
- roleplaying
- full precision
- float 32
- ultra quality
- swearing
- extreme swearing
- rp
- graphic horror
- horror
- nsfw
- llama3
- not-for-all-audiences
- mergekit
pipeline_tag: text-generation
Quants uploading...
L3-SMB-Grand-Story-The-Reaper-20.7B-GGUF
Grand Story version with 20X Brainstorm, set to "unbalanced" (this will be explained in the updated model card) to increase creativity.
Adjust repeat penalty as noted below to control this feature.
WARNING: Uncensored. Model can and will output NSFW content, content of a graphic horror nature, etc etc.
Model requires:
- Llama3 template and/or Command-R
- Max context 8k/8192, with rope 32k or higher.
- Repeat penalty at 1.1 min, higher for roleplay / turn based chat (1.12-1.14).
- Temp range 0 to 2. Suggest starting at .2 to .5, as this model runs hots.
Model card with examples to update shortly.