VizorZ0042
/

Perfected-AI-Sampler-Parameters_All-Models-All-Cases

Model card Files Files and versions

xet

Community

VizorZ0042 commited on Jan 6

Commit

82bd11a

verified ·

1 Parent(s): 17188bd

Small changes to README.md

Browse files

Filled out more info for V1

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -129,7 +129,7 @@ Eta helps to increase the frequency of temperature updates; smaller - stable and
 Never managed to get stable enough results for very long period of progression, so I personally avoid it and use strict settings instead.
 </details>
 <details><summary>Smoothing Curve (new):</summary>
-Dynamically adjusts the penalty, temperature, probability to avoid sudden changes; 1 and lower.
 Has stronger effect with higher Repetition Penalty.
@@ -159,7 +159,9 @@ Probability - the chance for Threshold to cutoff the desired most likely tokens.
 Very fine with very good creativity, level of details, emotional connections.
-Might confuse things like character names, species and etc (due to high Temperature and not low enough Top-A). **In such cases lower Repetition penalty to 1.02612**
 </details>
 <details><summary>V2 **-INSANE-DETAIL/ATTENTION-**</summary>
 <img src="https://gitlab.com/Azuro721/trueperfect-ai/-/raw/main/PERF2.png" style="float:right; width:200px; height:300px; padding:10px;">
@@ -211,7 +213,7 @@ Temperature 2.4 with Top-K 206 and TFS 0.8413 will output more attentive results
 Temperature 1.2 with Top-K 206 and TFS 0.8413 will output slightly more attentive results, with even less variety, emotions and "surprising" moments.
 </details>
-<details><summary>Repetition penalty:</summary>
 Base value: 1.12082, which will output more creative, emotional, varied, smart and "exciting" results. But tends to have issues with asterisks and quotation marks. Good as an **assistant**. Similar to 1.02612, but with more creativity, less descriptions, faster pace, more interesting responses across multiple characters simultaneously.
 1.121: an alternative variant of 1.12082, which might fix issues with overly descriptive outputs, but 1.12082 is preferred and context and/or initial input (first) should be adjusted instead.

 Never managed to get stable enough results for very long period of progression, so I personally avoid it and use strict settings instead.
 </details>
 <details><summary>Smoothing Curve (new):</summary>
+Dynamically adjusts the Penalty, temperature, probability to avoid sudden changes; 1 and lower.
 Has stronger effect with higher Repetition Penalty.
 Very fine with very good creativity, level of details, emotional connections.
+Might confuse things like character names, species and etc (due to high Temperature and not low enough Top-A). **In such cases lower Repetition Penalty to 1.02612**
+Top-A 0.043725 might work well only with Repetition Penalty 1.02612, but better with **V2**
 </details>
 <details><summary>V2 **-INSANE-DETAIL/ATTENTION-**</summary>
 <img src="https://gitlab.com/Azuro721/trueperfect-ai/-/raw/main/PERF2.png" style="float:right; width:200px; height:300px; padding:10px;">
 Temperature 1.2 with Top-K 206 and TFS 0.8413 will output slightly more attentive results, with even less variety, emotions and "surprising" moments.
 </details>
+<details><summary>Repetition Penalty:</summary>
 Base value: 1.12082, which will output more creative, emotional, varied, smart and "exciting" results. But tends to have issues with asterisks and quotation marks. Good as an **assistant**. Similar to 1.02612, but with more creativity, less descriptions, faster pace, more interesting responses across multiple characters simultaneously.
 1.121: an alternative variant of 1.12082, which might fix issues with overly descriptive outputs, but 1.12082 is preferred and context and/or initial input (first) should be adjusted instead.