Skip to content

Support IQ2_XXS GGML dequantization #32348

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
Closed
wants to merge 5 commits into from
Closed

Support IQ2_XXS GGML dequantization #32348

wants to merge 5 commits into from

Conversation

@Isotr0py
Copy link
Collaborator

@Isotr0py Isotr0py commented Jul 31, 2024 •
edited
Loading

What does this PR do?

  • Add support for IQ2_XXS ggml type dequantization

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

cc @SunMarc @LysandreJik

Isotr0py
Isotr0py commented Jul 31, 2024
View reviewed changes
src/transformers/integrations/ggml_utils.py
Comment on lines +1 to +7
# Constants for ggml imatrix dequantization
# migrate from https://github.com/ggerganov/ggml/blob/3f5a4bbe59285c0f679b376f6259187d5514ff9c/src/ggml-common.h#L437
import numpy as np


IQ2XXS_GRID = np.array([
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

How can we bypass make style for this file? This is copied and translated from source code of llama.cpp. I would like to keep the style align with source code.

Copy link
Member

Choose a reason for hiding this comment

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

Make sense ! WDYT @ArthurZucker ? Is this something we want ? I also see that there is a exclude_folders var in the makefile

Copy link
Collaborator

Choose a reason for hiding this comment

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

we usually use # fmt: skip

@Isotr0py
Copy link
Collaborator Author

Isotr0py commented Aug 7, 2024

@SunMarc Could you please take a look at this? Thanks very much!

SunMarc
SunMarc approved these changes Aug 7, 2024
View reviewed changes
Copy link
Member

@SunMarc SunMarc left a comment

Choose a reason for hiding this comment

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

Thanks for your contributions as always @Isotr0py ! Nice work !

src/transformers/integrations/ggml_utils.py
Comment on lines +1 to +7
# Constants for ggml imatrix dequantization
# migrate from https://github.com/ggerganov/ggml/blob/3f5a4bbe59285c0f679b376f6259187d5514ff9c/src/ggml-common.h#L437
import numpy as np


IQ2XXS_GRID = np.array([
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
Copy link
Member

Choose a reason for hiding this comment

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

Make sense ! WDYT @ArthurZucker ? Is this something we want ? I also see that there is a exclude_folders var in the makefile

@SunMarc SunMarc requested a review from ArthurZucker August 7, 2024 11:54
ArthurZucker
ArthurZucker approved these changes Aug 22, 2024
View reviewed changes
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

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

SOrry for the late review!

src/transformers/integrations/ggml_utils.py
Comment on lines +1 to +7
# Constants for ggml imatrix dequantization
# migrate from https://github.com/ggerganov/ggml/blob/3f5a4bbe59285c0f679b376f6259187d5514ff9c/src/ggml-common.h#L437
import numpy as np


IQ2XXS_GRID = np.array([
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
Copy link
Collaborator

Choose a reason for hiding this comment

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

we usually use # fmt: skip

src/transformers/integrations/ggml_utils.py
Comment on lines +6 to +71
IQ2XXS_GRID = np.array([
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
])
Copy link
Collaborator

Choose a reason for hiding this comment

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

Suggested change
IQ2XXS_GRID = np.array([
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
])
IQ2XXS_GRID = np.array([0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819, 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b, 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808, 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b, 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819, 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08, 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08, 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808, 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808, 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819, 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08, 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908, 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819, 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808, 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808, 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908, 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808, 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08, 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819, 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819, 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908, 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19, 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b, 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808, 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908, 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08, 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819, 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808, 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808, 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19, 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819, 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b, 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08, 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808, 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908, 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b, 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819, 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08, 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808, 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b, 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908, 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908, 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b, 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808, 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b, 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b, 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808, 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19, 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,]) # fmt: skip

@Isotr0py
Copy link
Collaborator Author

#32625 would be a better solution which used the dequantization function introduced in latest v0.10.0 gguf package and cleaned up the code. And it's nearly ready for review, once v0.10.0 gguf-py package is uploaded to pypi.

So I think this PR is no needed anymore :)

@Isotr0py Isotr0py closed this Aug 22, 2024
@Isotr0py Isotr0py deleted the gguf-iq branch August 22, 2024 14:43
@ArthurZucker
Copy link
Collaborator

Sure! 🤗

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

Reviewers

@ArthurZucker ArthurZucker ArthurZucker approved these changes

@SunMarc SunMarc SunMarc approved these changes

Assignees

No one assigned

Labels

Quantization

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@Isotr0py @ArthurZucker @SunMarc @amyeroberts