mradermacher commited on
Commit
c50c499
1 Parent(s): 9a2df4a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -10
README.md CHANGED
@@ -155,16 +155,6 @@ Update 2024-07: llama.cpp probably has most of the features needed to make this
155
 
156
  Update 2024-09: just looked at implementing it, and no, the problems that keep me from doing it are still there :(. Must have fantasized it!!?
157
 
158
- ## Why are there so many imatrix quants where llama.cpp crashes?
159
-
160
- Because llama.cpp developers see imatrix quants as a useless gimmick, are not very interested in fixing bugs,
161
- instead of mostly just wanting to ignore the problem, and considers merged models as mostly useless. They
162
- are more interested in blaming their users.
163
-
164
- As a result I have given up reporting bugs, and my efforts in providing imatrix quants will be reduced.
165
-
166
- https://github.com/ggerganov/llama.cpp/issues/6841 is the issue ticket that escalated this.
167
-
168
  ## So who is mradermacher?
169
 
170
  Nobody has asked this, but since there are people who really deserve mention, I'll put this here. "mradermacher" is just a
 
155
 
156
  Update 2024-09: just looked at implementing it, and no, the problems that keep me from doing it are still there :(. Must have fantasized it!!?
157
 
 
 
 
 
 
 
 
 
 
 
158
  ## So who is mradermacher?
159
 
160
  Nobody has asked this, but since there are people who really deserve mention, I'll put this here. "mradermacher" is just a