calcuis commited on
Commit
4797315
1 Parent(s): 4e741ea

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -34,9 +34,9 @@ tags:
34
 
35
  ### Bug reports (or brief review)
36
  - t/q1_0 and t/q2_0; doesn't work; encountering np.uint32(34 & 35) is not a valid GGMLQuantizationType error
37
- - q2_k is super fast; but picture looks like x-ray film; might be good for medical research or abstract stylist/artist
38
- - q3 family is very fast; finger problem can be easily detected but picture quality is interestingly good
39
- - notice the same file size in 0 and s models; still keep them all here; see who can help out to fix it
40
  - q4 and above should be no problem for general to high quality production
41
 
42
  ### Upper tier sets
 
34
 
35
  ### Bug reports (or brief review)
36
  - t/q1_0 and t/q2_0; doesn't work; encountering np.uint32(34 & 35) is not a valid GGMLQuantizationType error
37
+ - q2_k is super fast; but picture looks like x-ray film; might be good for medical research or abstract stylist
38
+ - q3 family is very fast; finger issue can be easily detected but picture quality is interestingly good
39
+ - notice the same file size in 0 and s models; still keep them all here; see who can help out on that
40
  - q4 and above should be no problem for general to high quality production
41
 
42
  ### Upper tier sets