DavidAU commited on
Commit
0a1008b
1 Parent(s): 1a22d31

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -54,9 +54,15 @@ of prompts in usage. This is a factor due to the precision upscale.
54
 
55
  Doing this will ensure the quality of the upscale is maximized in the GGUFs.
56
 
57
- GPTQers: Suggest 4bit-Act 32 TRUE for best results.*
58
 
59
- EXL2ers: Suggest Min 4.5 BPW or higher ; 6 BPW and up is especially potent.*
 
 
 
 
 
 
60
 
61
  Happy GGUFing, EXL2ing, GPTQing, AWQing, HQQing and of course "Merging".
62
 
 
54
 
55
  Doing this will ensure the quality of the upscale is maximized in the GGUFs.
56
 
57
+ /* GPTQers:
58
 
59
+ Suggest 4bit-Act32 TRUE for best results.
60
+
61
+ /* EXL2ers:
62
+
63
+ Suggest Min 4.5 BPW or higher ; 6 BPW and up is especially potent.
64
+ Strongly suggest you do not reduce layer bit count, as this will affect depth and nuance.
65
+ The more BPW the better.
66
 
67
  Happy GGUFing, EXL2ing, GPTQing, AWQing, HQQing and of course "Merging".
68