DavidAU commited on
Commit
ffa612d
1 Parent(s): c0b9ef6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -71,7 +71,11 @@ I suggest downloading both (of the same quant) and test in your use case(s).
71
 
72
  The "flavoring" each brings to Command-R will differ - some slightly, some by a lot - depending on the prompt(s) used / use case(s).
73
 
74
- This model requires "Command-R" template, and has a max context of 128k (131,000).
 
 
 
 
75
 
76
  --- Quants uploading... Model card with examples pending updates. ---
77
 
 
71
 
72
  The "flavoring" each brings to Command-R will differ - some slightly, some by a lot - depending on the prompt(s) used / use case(s).
73
 
74
+ NOTES:
75
+
76
+ - This model requires "Command-R" template, responds to standard parameters, and has a max context of 128k (131,000).
77
+ - "IQ" quants will be uploaded first, as the Imatrix effect is far stronger in these than "Q" quants.
78
+ - 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.
79
 
80
  --- Quants uploading... Model card with examples pending updates. ---
81