Text Generation
GGUF
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
bfloat16
role play
128k context
llama3.2
imatrix
conversational
General overview / discussion.
#2
by
VizorZ0042
- opened
Hello again dear DavidAU.
I've been testing this model too, and seems like it's censored too?
Here are the results:
CLASS1 settings with Optimal Enhancement. KoboltGPT card template.
Overall this model is similar to Llama-3.2-1B-Instruct-NEO-SI-FI, but provides a bit more vivid scenes and a bit slower progression, with a bit more complex cards and instructions.
This model is has the "regular" Meta Instruct as the base model - censorship included.
RE: Differences ; Interesting observation.
That effect is stronger than expected. (?)
That effect is stronger than expected. (?)
Yeah, a bit stronger compared to 1B; I can run 10 passes with exact instructions, context and card to show you the difference.