Skip to content
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

[FIX] fix test_integration #497

Merged
merged 1 commit into from
Oct 29, 2024
Merged

[FIX] fix test_integration #497

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions gptqmodel/integration/optimum/hf_quantizer_gptq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,8 @@

from transformers.utils import is_optimum_available, is_torch_available, logging
from transformers.utils.quantization_config import QuantizationConfigMixin

from transformers import __version__ as transformers_version
from packaging import version
if is_torch_available():
import torch

Expand Down Expand Up @@ -79,10 +80,19 @@ def _process_model_after_weight_loading(self, model: "PreTrainedModel", **kwargs
self.optimum_quantizer.quantize_model(model, self.quantization_config.tokenizer)
model.config.quantization_config = GPTQConfig.from_dict(self.optimum_quantizer.to_dict())

def _is_transformers_new_version(self):
return version.parse(transformers_version) >= version.parse("4.46.0")

@property
def is_trainable(self, model: Optional["PreTrainedModel"] = None):
return True

@property
def is_serializable(self):
return True
if self._is_transformers_new_version():
def is_serializable_fn(safe_serialization=True):
return True

return is_serializable_fn
else:
return True
Loading