Text Generation
GGUF
English
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
story
writing
fiction
roleplaying
horror
general usage
roleplay
neo quant
fantasy
story telling
ultra high precision
Inference Endpoints
imatrix
conversational
Update README.md
Browse files
README.md
CHANGED
@@ -82,7 +82,7 @@ One version is not stronger than the other, they are different and result in dif
|
|
82 |
|
83 |
<B>Recommended Quants:</B>
|
84 |
|
85 |
-
This chart shows the order in terms of "BPW" for each quant with "IQ1_S" with the least, and Q8_0 with the most:
|
86 |
|
87 |
IQ1_S | IQ1_M
|
88 |
|
@@ -98,8 +98,13 @@ Q6_K
|
|
98 |
|
99 |
Q8_0
|
100 |
|
|
|
|
|
|
|
101 |
(not all quants may be at this repo)
|
102 |
|
|
|
|
|
103 |
- The LOWER the quant the STRONGER the Imatrix effect is, and therefore the stronger the horror "tint" so to speak
|
104 |
- Due to the unique nature of this project, quants IQ1s to IQ4s are recommended for maximum horror effect with IQ4_XS the most balanced in terms of power and bits.
|
105 |
- Secondaries are Q2s-Q4s. Imatrix effect is still strong in these quants.
|
|
|
82 |
|
83 |
<B>Recommended Quants:</B>
|
84 |
|
85 |
+
This chart shows the order in terms of "BPW" for each quant with "IQ1_S" with the least, and "Q8_0" with the most:
|
86 |
|
87 |
IQ1_S | IQ1_M
|
88 |
|
|
|
98 |
|
99 |
Q8_0
|
100 |
|
101 |
+
More BPW mean better quality, but higher VRAM requirements (and larger file size) and lower Tokens per second.
|
102 |
+
The larger the model in terms of parameters the lower the size of quant you can run with less quality losses.
|
103 |
+
|
104 |
(not all quants may be at this repo)
|
105 |
|
106 |
+
Suggestions for this model:
|
107 |
+
|
108 |
- The LOWER the quant the STRONGER the Imatrix effect is, and therefore the stronger the horror "tint" so to speak
|
109 |
- Due to the unique nature of this project, quants IQ1s to IQ4s are recommended for maximum horror effect with IQ4_XS the most balanced in terms of power and bits.
|
110 |
- Secondaries are Q2s-Q4s. Imatrix effect is still strong in these quants.
|