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
Inference Endpoints
imatrix
conversational
Update README.md
Browse files
README.md
CHANGED
@@ -126,10 +126,6 @@ QUANT CHOICE(S):
|
|
126 |
Higher quants will have more detail, nuance and in some cases stronger "emotional" levels. Characters will also be
|
127 |
more "fleshed out" too. Sense of "there" will also increase.
|
128 |
|
129 |
-
Q4KM/Q4KS are good, strong quants however if you can run Q5, Q6 or Q8 - go for the highest quant you can.
|
130 |
-
|
131 |
-
This repo also has 3 "ARM" quants for computers that support this quant. If you use these on a "non arm" machine token per second will be very low.
|
132 |
-
|
133 |
IQ4XS: Due to the unusual nature of this quant (mixture/processing), generations from it will be different then other quants.
|
134 |
|
135 |
You may want to try it / compare it to other quant(s) output.
|
|
|
126 |
Higher quants will have more detail, nuance and in some cases stronger "emotional" levels. Characters will also be
|
127 |
more "fleshed out" too. Sense of "there" will also increase.
|
128 |
|
|
|
|
|
|
|
|
|
129 |
IQ4XS: Due to the unusual nature of this quant (mixture/processing), generations from it will be different then other quants.
|
130 |
|
131 |
You may want to try it / compare it to other quant(s) output.
|