add use_hf_format for export_compressed_model #1379
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
Signed-off-by: Xin He <[email protected]>
hshen14
reviewed
Nov 16, 2023
hshen14
reviewed
Nov 16, 2023
hshen14
approved these changes
Nov 16, 2023
Signed-off-by: Xin He <[email protected]>
hshen14
approved these changes
Nov 16, 2023
changwangss
approved these changes
Nov 17, 2023
xin3he
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Type of Change
feature
Description
Huggingface GPTQ models are using a popular repo https://github.com/qwopqwop200/GPTQ-for-LLaMa for compression.
I add an args in get_compressed_model(use_hf_fomat=True) to align with the popular one.
The main change for this arg is as below:
1: compression_dim: weight = 1, zeros = 0 and both are transposed.
2: zeros -= 1 before compression. Why we need it?
3: g_idx: use same number for one group instead of recording the channel order.
4. parameter name changed, such as 'packed_weight' -> 'qweight'.
5. zeros is always needed even for sym.
Expected Behavior & Potential Risk
UT pass
How has this PR been tested?
local test
Dependency Change?
N/A