adapt transformers 4.37 loading #1606
Merged
Conversation
This file contains 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: changwangss <[email protected]>
for more information, see https://pre-commit.ci
Signed-off-by: chensuyue <[email protected]>
xin3he
approved these changes
Feb 5, 2024
|
CI failed with performance gap but it seems caused by this PR, @chensuyue please give some helps. |
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Outdated suggestions cannot be applied.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
ticket: https://jira.devtools.intel.com/browse/ILITV-3414
root cause, transformers 4.37.2 limits pytorch_model.bin loading by https://github.com/huggingface/transformers/blob/v4.37.2/src/transformers/modeling_utils.py#L530
"model.safetensors" only support tensor values, the state_dict not only includes weight key and value but also has inc quantization config(str) with pytorch fx mode, so still keep the "pytorch_model.bin".
Description
Description
detail description
Expected Behavior & Potential Risk
the expected behavior that triggered by this PR
How has this PR been tested?
how to reproduce the test (including hardware information)
Dependency Change?
any library dependency introduced or removed