-
Notifications
You must be signed in to change notification settings - Fork 27.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Docs
] Add 4-bit serialization docs
#28182
[Docs
] Add 4-bit serialization docs
#28182
Conversation
Docs
] Add 4-bit serialization docs
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
docs/source/en/quantization.md
Outdated
@@ -468,6 +468,10 @@ Try 4-bit quantization in this [notebook](https://colab.research.google.com/driv | |||
|
|||
This section explores some of the specific features of 4-bit models, such as changing the compute data type, using the Normal Float 4 (NF4) data type, and using nested quantization. | |||
|
|||
#### Push 4-bit models on the Hub | |||
|
|||
If you have `bitsandbytes>=0.41.3`, you can serialize 4-bit models and push them on Hugging Face Hub. Simply call `model.push_to_hub()` after loading it in 4-bit precision. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the update! I think it would be nicer to include this here so it parallels the 8-bit section :)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AH thanks! good point, will do it now
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done, maybe it is a bit repetitive, lmk what do you think!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice, and then we can remove the #### Push 4-bit models on the Hub
section so its not as repetitive
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Okay , done!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great - thanks for adding!
* add 4-bit serialization docs * up * up
What does this PR do?
Follow up work from: #26037
Adds few lines in the documentation about serializing 4-bit models on the Hub
cc @amyeroberts @stevhliu