mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Update Low-VRAM-guide.md

Browse source
This commit is contained in:
oobabooga 2023-04-22 02:50:35 -03:00 • committed by GitHub
parent f5c36cca40
commit 6d4f131d0a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/Low-VRAM-guide.md
View file

@ -48,4 +48,4 @@ With this, I am able to load a 30b model into my RTX 3090, but it takes 10 secon
### DeepSpeed (experimental) ### DeepSpeed (experimental)
An experimental alternative to all of the above is to use DeepSpeed: [guide](https://github.com/oobabooga/text-generation-webui/wiki/DeepSpeed). An experimental alternative to all of the above is to use DeepSpeed: [guide](DeepSpeed.md).