DavidAU commited on
Commit
36bbdf0
1 Parent(s): 31a3385

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -75,12 +75,13 @@ These are labeled in the filenames with "V1" and "V2" accordingly.
75
  I suggest downloading both (of the same quant) and test in your use case(s).
76
 
77
  The "flavoring" each brings to Command-R will differ - some slightly, some by a lot - depending on the prompt(s) used / use case(s).
 
78
 
79
  NOTES:
80
 
81
  - This model requires "Command-R" template, responds to standard parameters, and has a max context of 128k (131,000).
82
  - "IQ" quants will be uploaded first, as the Imatrix effect is far stronger in these than "Q" quants.
83
- - IQ4 is the most powerful/balanced in terms of raw power, however IQ3/IQ2 may be stronger "horror" wise do to increased IMATRIX effects the lower you go in terms of bit level.
84
 
85
  <b>Optional Enhancement:</B>
86
 
 
75
  I suggest downloading both (of the same quant) and test in your use case(s).
76
 
77
  The "flavoring" each brings to Command-R will differ - some slightly, some by a lot - depending on the prompt(s) used / use case(s).
78
+ One version is not stronger than the other, they are different and result in different "horror" effects so to speak.
79
 
80
  NOTES:
81
 
82
  - This model requires "Command-R" template, responds to standard parameters, and has a max context of 128k (131,000).
83
  - "IQ" quants will be uploaded first, as the Imatrix effect is far stronger in these than "Q" quants.
84
+ - IQ4 is the most powerful/balanced in terms of raw power, however IQ3/IQ2 may be stronger "horror" wise due to increased IMATRIX effects the lower you go in terms of bit level.
85
 
86
  <b>Optional Enhancement:</B>
87