FutureWarning close

Beginners
1

how to close the message

EMBEDDING_MODEL_NAME = "hkunlp/instructor-large"
HuggingFaceEmbeddings(
            model_name=EMBEDDING_MODEL_NAME,
            model_kwargs={"device": device_type},
        )

conda\envs\lang\Lib\site-packages\sentence_transformers\models\Dense.py:63: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  model.load_state_dict(torch.load(os.path.join(input_path, 'pytorch_model.bin'), map_location=torch.device('cpu')))
2024-08-27 16:07:29,795 - INFO - ingest.py:168 - Loaded embeddings from hkunlp/instructor-large
2

You can set "weights_only = True "

3

The same warning problem with this

HuggingFaceEmbeddings(
            model_name=EMBEDDING_MODEL_NAME,
            model_kwargs={"device": device_type, "weights_only": True},
        )
4

hi @alice86

transformers.utils.logging.set_verbosity_error() didn’t work for me, because warning doesn’t come from logging. But this one helps:

Adding the following will filter out FutureWarning.

import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)

I tested it for UserWarning.

5

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.