DavidAU commited on
Commit
ea4ed8b
1 Parent(s): ccbfef5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -119,6 +119,19 @@ Special note on Q2k/Q3 quants:
119
  You may need to use temp 4 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
120
  of these quants will function better. As of this writing, q3KM tests and works at temp 4 or lower without issues.
121
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  <B>Model "DNA":</B>
123
 
124
  Special thanks to the incredible work of the model makers "TheDrummer", "anthracite-org", and "nothingiisreal".
 
119
  You may need to use temp 4 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
120
  of these quants will function better. As of this writing, q3KM tests and works at temp 4 or lower without issues.
121
 
122
+ <B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
123
+
124
+ This a "Class 1" model:
125
+
126
+ For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
127
+
128
+ [ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
129
+
130
+ You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
131
+
132
+ [ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
133
+
134
+
135
  <B>Model "DNA":</B>
136
 
137
  Special thanks to the incredible work of the model makers "TheDrummer", "anthracite-org", and "nothingiisreal".