Anthonyg5005 commited on
Commit
114db8f
1 Parent(s): adefdbb

edit instructions

Browse files
auto-exl2-upload/INSTRUCTIONS.txt CHANGED
@@ -23,6 +23,8 @@ Make sure to also have a lot of RAM depending on the model.
23
 
24
  If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the finished BPW as it will start from the beginning. You may also use ctrl + c pause at any time during the quant process.
25
 
 
 
26
  Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions
27
 
28
 
 
23
 
24
  If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the finished BPW as it will start from the beginning. You may also use ctrl + c pause at any time during the quant process.
25
 
26
+ To add more options to the quantization process, you can add them to line 170. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
27
+
28
  Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions
29
 
30
 
auto-exl2-upload/auto-exl2-upload.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d701183fd79366ad97a3426080d22b094cd56df40960e7ef16d6d062d3a7c35
3
- size 6882
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde2bead3780510e4231bf7df034861e3f74dddc8b344581e4aff0e8f88d4681
3
+ size 6944
exl2-multi-quant-local/INSTRUCTIONS.txt CHANGED
@@ -23,6 +23,8 @@ Make sure to also have a lot of RAM depending on the model.
23
 
24
  If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the finished BPW as it will start from the beginning. You may also use ctrl + c pause at any time during the quant process.
25
 
 
 
26
  Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions
27
 
28
 
 
23
 
24
  If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the finished BPW as it will start from the beginning. You may also use ctrl + c pause at any time during the quant process.
25
 
26
+ To add more options to the quantization process, you can add them to line 126. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
27
+
28
  Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions
29
 
30
 
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:f0accdc4d09d944d44db85e455e1195e5d2e6e535bcc559a314f2b09dc524552
3
- size 5923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31eea2f70d09176f279461f9d7fddd5b7edf5eb129a957c792596c984679a524
3
+ size 5985