Hugging Face's logo

Anthonyg5005
/
hf-scripts

English
Model card Files Community
1
Anthonyg5005 commited on
Commit
711eae9
·
1 Parent(s): 850fc96

remove windows tag from url

Browse files
Files changed (5) hide show
  1. auto-exl2-upload/INSTRUCTIONS.txt +2 -2
  2. auto-exl2-upload/auto-exl2-upload.zip +2 -2
  3. exl2-multi-quant-local/INSTRUCTIONS.txt +2 -2
  4. exl2-multi-quant-local/exl2-multi-quant-local.zip +2 -2
  5. exl2-multi-quant-local/exl2-quant.py +0 -1
auto-exl2-upload/INSTRUCTIONS.txt CHANGED
@@ -1,10 +1,10 @@
1
  For NVIDIA cards install the CUDA toolkit
2
 
3
  Nvidia Maxwell or higher
4
- https://developer.nvidia.com/cuda-downloads?target_os=Windows&target_arch=x86_64
5
 
6
  Nvidia Kepler or higher
7
- https://developer.nvidia.com/cuda-11-8-0-download-archive?target_os=Windows&target_arch=x86_64
8
 
9
 
10
  Haven't done much testing but for Windows, Visual Studio with desktop development for C++ might be required. I've gotten cl.exe errors on a previous install
 
1
  For NVIDIA cards install the CUDA toolkit
2
 
3
  Nvidia Maxwell or higher
4
+ https://developer.nvidia.com/cuda-downloads
5
 
6
  Nvidia Kepler or higher
7
+ https://developer.nvidia.com/cuda-11-8-0-download-archive
8
 
9
 
10
  Haven't done much testing but for Windows, Visual Studio with desktop development for C++ might be required. I've gotten cl.exe errors on a previous install
auto-exl2-upload/auto-exl2-upload.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a349a20b47f44a0b83615faa7f45efdea6be73e71e50b2f90ff0b84242605b07
3
- size 6945
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6010e64b052531453839a1ea10c85e8c6ab2251b4ec913157a7b5611882924a
3
+ size 6917
exl2-multi-quant-local/INSTRUCTIONS.txt CHANGED
@@ -1,10 +1,10 @@
1
  For NVIDIA cards install the CUDA toolkit
2
 
3
  Nvidia Maxwell or higher
4
- https://developer.nvidia.com/cuda-downloads?target_os=Windows&target_arch=x86_64
5
 
6
  Nvidia Kepler or higher
7
- https://developer.nvidia.com/cuda-11-8-0-download-archive?target_os=Windows&target_arch=x86_64
8
 
9
 
10
  Haven't done much testing but for Windows, Visual Studio with desktop development for C++ might be required. I've gotten cl.exe errors on a previous install
 
1
  For NVIDIA cards install the CUDA toolkit
2
 
3
  Nvidia Maxwell or higher
4
+ https://developer.nvidia.com/cuda-downloads
5
 
6
  Nvidia Kepler or higher
7
+ https://developer.nvidia.com/cuda-11-8-0-download-archive
8
 
9
 
10
  Haven't done much testing but for Windows, Visual Studio with desktop development for C++ might be required. I've gotten cl.exe errors on a previous install
exl2-multi-quant-local/exl2-multi-quant-local.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df071dea5e0f8a33b2828168f9c60b0218b00383a15c3fe16fff9a93bd0f400c
3
- size 5985
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a18897cac314755429d291fad350608ef63b4e2fc7ffc0586f7900162f87c81
3
+ size 5957
exl2-multi-quant-local/exl2-quant.py CHANGED
@@ -53,7 +53,6 @@ else:
53
  print("Skipping login... (Unable to access private or gated models)")
54
  tfound = "false but skipped" #doesn't matter what this is, only false is used
55
  time.sleep(3)
56
-
57
  clear_screen()
58
 
59
  #get original model repo url
 
53
  print("Skipping login... (Unable to access private or gated models)")
54
  tfound = "false but skipped" #doesn't matter what this is, only false is used
55
  time.sleep(3)
 
56
  clear_screen()
57
 
58
  #get original model repo url