🚨🚨🚨 [Quantization] Store the original dtype in the config as a private attribute 🚨🚨🚨
#26761
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
younesbelkada
commented
Oct 12, 2023
|
The documentation is not available anymore as the PR was closed or merged. |
src/transformers/modeling_utils.py
Outdated
| # one the weights have been quantized | ||
| # Note that once you have loaded a quantized model, you can't change its dtype so this will | ||
| # remain a single source of truth | ||
| config._quantization_original_dtype = torch_dtype |
There was a problem hiding this comment.
Suggested change
| config._quantization_original_dtype = torch_dtype | |
| config._pre_quantization_dtype = torch_dtype |
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
ArthurZucker
approved these changes
Oct 13, 2023
Comment on lines
+857
to
+858
| # pop the `_pre_quantization_dtype` as torch.dtypes are not serializable. | ||
| _ = serializable_config_dict.pop("_pre_quantization_dtype", None) |
There was a problem hiding this comment.
we pop it because it should not be saved no?
Comment on lines
+3189
to
+3190
| # Note that once you have loaded a quantized model, you can't change its dtype so this will | ||
| # remain a single source of truth |
There was a problem hiding this comment.
Might be needed in the quantizer config?
There was a problem hiding this comment.
I think it is ok since users can always load back quantized models with new torch_dtype making that _pre_quantization_dtype obsolete
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Quantization] Store the original dtype in the config as a private attributeQuantization] Store the original dtype in the config as a private attribute 🚨🚨🚨
Merged
EduardoPach
pushed a commit
to EduardoPach/transformers
that referenced
this pull request
Nov 19, 2023
…ate attribute 🚨🚨🚨 (huggingface#26761) * First step * fix * add adjustements for gptq * change to `_pre_quantization_dtype` * Update src/transformers/modeling_utils.py Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * fix serialization * Apply suggestions from code review Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * fixup --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
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.
What does this PR do?
First step of an alternative design of #26560
For quantized models, instead of introducing a complex logic of retrieving the original weights dtype, I propose to simply add a private attribute
_quantization_original_dtypein the config object.tomethod does not need to be touched here astocannot be called on quantized models (but for GPTQ models you can calltoto perform device placement only - not for dtype casting)that way we could adapt #26560 to simply check if the config has the attribute
_quantization_original_dtypewhich is the case only for quantized models, else retrieve the dtype by retrieving the dtype of the linear layer weights in a classic manner.cc @LysandreJik