Text Generation
GGUF
English
mixture of experts
Mixture of Experts
4x8B
Llama3 MOE
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
swearing
rp
horror
mergekit
llama-3
llama3
conversational
Update README.md
Browse files
README.md
CHANGED
@@ -48,15 +48,17 @@ models of 8B each into one massive powerhouse at 25B parameters (equal to 32B -
|
|
48 |
|
49 |
This model's instruction following, and output generation for creative writing, prose, fiction and role play are exceptional.
|
50 |
|
51 |
-
It excels at description, dialog, imagery, metaphors, and prose -
|
52 |
|
53 |
-
It is also not afraid, and will not pull its punches.
|
|
|
|
|
54 |
|
55 |
It can do horror just as easily as it can do romance.
|
56 |
|
57 |
-
Most notably dialog is very "un-ai" like.
|
58 |
|
59 |
-
(lots of different examples below, including 2, 3 and 4 experts)
|
60 |
|
61 |
And it is fast: 34 t/s (2 experts) on a low end 16GB card, Q3KS.
|
62 |
|
|
|
48 |
|
49 |
This model's instruction following, and output generation for creative writing, prose, fiction and role play are exceptional.
|
50 |
|
51 |
+
It excels at description, dialog, imagery, metaphors, and prose - and shows great variations in sentence / paragraph size, length, and composition.
|
52 |
|
53 |
+
It is also not afraid, and will not pull its punches.
|
54 |
+
|
55 |
+
And it has a sense of humor too.
|
56 |
|
57 |
It can do horror just as easily as it can do romance.
|
58 |
|
59 |
+
Most notably dialog is very "un-ai" like, combined with prose (short, and terse at times).
|
60 |
|
61 |
+
(lots of different examples below, including 2, 3 and 4 experts and different genres)
|
62 |
|
63 |
And it is fast: 34 t/s (2 experts) on a low end 16GB card, Q3KS.
|
64 |
|