Text Generation
GGUF
English
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
llama-3
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
bfloat16
brainstorm 40x
swearing
rp
horror
llama3
mergekit
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -197,6 +197,12 @@ more "fleshed out" too. Sense of "there" will also increase.
|
|
| 197 |
|
| 198 |
Q4KM/Q4KS are good, strong quants however if you can run Q5, Q6 or Q8 - go for the highest quant you can.
|
| 199 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
Special note on Q2k/Q3 quants:
|
| 201 |
|
| 202 |
You may need to use temp 2 or lower with these quants (1 or lower for q2k). Just too much compression at this level, damaging the model. I will see if Imatrix versions
|
|
|
|
| 197 |
|
| 198 |
Q4KM/Q4KS are good, strong quants however if you can run Q5, Q6 or Q8 - go for the highest quant you can.
|
| 199 |
|
| 200 |
+
This repo also has 3 "ARM" quants for computer that support this quant.
|
| 201 |
+
|
| 202 |
+
IQ4XS: Due to the unusual nature of this quant (mixture/processing), generations from it will be different then other quants.
|
| 203 |
+
|
| 204 |
+
You may want to try it / compare it to other quant(s) output.
|
| 205 |
+
|
| 206 |
Special note on Q2k/Q3 quants:
|
| 207 |
|
| 208 |
You may need to use temp 2 or lower with these quants (1 or lower for q2k). Just too much compression at this level, damaging the model. I will see if Imatrix versions
|