Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Allow ModelCompressor.from_pretrained to load from quantization_config, not compression config #207

Merged
merged 4 commits into from
Nov 23, 2024
Merged

Allow ModelCompressor.from_pretrained to load from quantization_config, not compression config #207

merged 4 commits into from
Nov 23, 2024

Conversation

horheynm
Copy link
Member

@horheynm horheynm commented Nov 18, 2024 •
edited
Loading

Fix bugs on loading the compression_config to quantization_config. Loading from the former is now removed
Added minor doc string and type checks for confusing output from functions

dsikka
dsikka requested changes Nov 20, 2024
View reviewed changes
Copy link
Contributor

@dsikka dsikka left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

comment

@horheynm
Copy link
Member Author

/ready

@dsikka dsikka self-requested a review November 22, 2024 14:40
dsikka
dsikka previously approved these changes Nov 22, 2024
View reviewed changes
@horheynm
Copy link
Member Author

Might not need
QuantizationConfigHFQuantizer

please hold merge

dsikka
dsikka reviewed Nov 22, 2024
View reviewed changes
Copy link
Contributor

@dsikka dsikka left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR looks good but I dont see the connection from your description as to why this is needed for run_compressed=False

@horheynm
Copy link
Member Author

@dsikka
Yes you are right, previously there was custom config class inheriting QuantizationConfig that i no longer use.
i will update the title

@horheynm horheynm changed the title allow HFQuantizer to run run_compressed=False mode Allow ModelCompressor.from_pretrained to load from quantization_config, not compression config Nov 22, 2024
@mgoin mgoin merged commit a26c03a into main Nov 23, 2024
1 check passed
@mgoin mgoin deleted the run_comp-hf_quant branch November 23, 2024 00:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dsikka dsikka dsikka approved these changes

@mgoin mgoin mgoin approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@horheynm @mgoin @dsikka