Skip to content

Conversation

@EAddario
Copy link
Contributor

This PR updates llama-quantize README doc. It removes old information and adds current capabilities and examples

@EAddario EAddario changed the title Update README.md quantize: update README.md Jul 27, 2025
Co-authored-by: Sigbjørn Skjæret <[email protected]>
@CISC CISC merged commit 7f97599 into ggml-org:master Jul 27, 2025
2 checks passed
@EAddario
Copy link
Contributor Author

Thank you @CISC

@EAddario EAddario deleted the quantize branch July 27, 2025 21:33
@jacekpoplawski
Copy link
Contributor

jacekpoplawski commented Jul 28, 2025

--include-weights use an importance matrix for tensor(s) in the list. Cannot be used with --exclude-weights
--exclude-weights use an importance matrix for tensor(s) in the list. Cannot be used with --include-weights

Isn't it a typo?

@EAddario
Copy link
Contributor Author

Sorry, not seeing the typo. Time to increase my prescription 👓?

@CISC
Copy link
Collaborator

CISC commented Jul 28, 2025

Sorry, not seeing the typo. Time to increase my prescription 👓?

The latter should be don't use.

@EAddario
Copy link
Contributor Author

Ah... I see the issue now. I'll create a new PR in the next day or so to fix.
I'll also fix the meta-llama/Llama-3.1-8B table layout with a more aesthetically pleasing version

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants