# Can't import Pipeline from Transformers **URL:** **Author:** ![aalekh29](https://avatars.discourse-cdn.com/v4/letter/a/e95f7d/32.png) [@aalekh29](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Faalekh29)%5C **Post date:** [August 21, 2024, 3:54pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcant-import-pipeline-from-transformers%2F103365%2F1 "2024-08-21T15:54:02Z") I have to work on GPT Neo model and generate text output by asking some questions (automotive related). I am doing NLP related work for first time. I am using Jupyter notebook and have installed pytorch, and transformers. But I am unable to import Pipeline to further write prompts. I have tried installing the latest version of pytorch and transformers as well as tried to work with older version of transformers as well !pip install transformers OR !pip install transformers==4.44.1 OR !pip install transformers==4.28.0 Here’s the error. [WINERROR126]: The specific module could not be found. * * * * * * OSError Traceback (most recent call last) Cell In[5], line 1 ----\> 1 from transformers import pipeline File ~\anaconda3\Lib\site-packages\transformers\__init_\_.py:26 23 from typing import TYPE\_CHECKING 25 # Check the dependencies satisfy the minimal versions required. —\> 26 from . import dependency\_versions\_check 27 from .utils import ( 28 OptionalDependencyNotAvailable, 29 \_LazyModule, (…) 48 logging, 49 ) 52 logger = logging.get\_logger( **name** ) # pylint: disable=invalid-name File ~\anaconda3\Lib\site-packages\transformers\dependency\_versions\_check.py:16 1 # Copyright 2020 The HuggingFace Team. All rights reserved. 2 # 3 # Licensed under the Apache License, Version 2.0 (the “License”); (…) 12 # See the License for the specific language governing permissions and 13 # limitations under the License. 15 from .dependency\_versions\_table import deps —\> 16 from .utils.versions import require\_version, require\_version\_core 19 # define which module versions we always want to check at run time 20 # (usually the ones defined in `install_requires` in setup.py) 21 # 22 # order specific notes: 23 # - tqdm must be checked before tokenizers 25 pkgs\_to\_check\_at\_runtime = [ 26 “python”, 27 “tqdm”, (…) 37 “pyyaml”, 38 ] File ~\anaconda3\Lib\site-packages\transformers\utils\__init_\_.py:34 25 from .constants import IMAGENET\_DEFAULT\_MEAN, IMAGENET\_DEFAULT\_STD, IMAGENET\_STANDARD\_MEAN, IMAGENET\_STANDARD\_STD 26 from .doc import ( 27 add\_code\_sample\_docstrings, 28 add\_end\_docstrings, (…) 32 replace\_return\_docstrings, 33 ) —\> 34 from .generic import ( 35 ContextManagers, 36 ExplicitEnum, 37 ModelOutput, 38 PaddingStrategy, 39 TensorType, 40 add\_model\_info\_to\_auto\_map, 41 add\_model\_info\_to\_custom\_pipelines, 42 cached\_property, 43 can\_return\_loss, 44 expand\_dims, 45 filter\_out\_non\_signature\_kwargs, 46 find\_labels, 47 flatten\_dict, 48 infer\_framework, 49 is\_jax\_tensor, 50 is\_numpy\_array, 51 is\_tensor, 52 is\_tf\_symbolic\_tensor, 53 is\_tf\_tensor, 54 is\_torch\_device, 55 is\_torch\_dtype, 56 is\_torch\_tensor, 57 reshape, 58 squeeze, 59 strtobool, 60 tensor\_size, 61 to\_numpy, 62 to\_py\_obj, 63 torch\_float, 64 torch\_int, 65 transpose, 66 working\_or\_temp\_dir, 67 ) 68 from .hub import ( 69 CLOUDFRONT\_DISTRIB\_PREFIX, 70 HF\_MODULES\_CACHE, (…) 96 try\_to\_load\_from\_cache, 97 ) 98 from .import\_utils import ( 99 ACCELERATE\_MIN\_VERSION, 100 ENV\_VARS\_TRUE\_AND\_AUTO\_VALUES, (…) 219 torch\_only\_method, 220 ) File ~\anaconda3\Lib\site-packages\transformers\utils\generic.py:462 458 return tuple(self[k] for k in self.keys()) 461 if is\_torch\_available(): → 462 import torch.utils.\_pytree as \_torch\_pytree 464 def \_model\_output\_flatten(output: ModelOutput) → Tuple[List[Any], “\_torch\_pytree.Context”]: 465 return list(output.values()), list(output.keys()) File ~\anaconda3\Lib\site-packages\torch\__init_\_.py:148 146 err = ctypes.WinError(ctypes.get\_last\_error()) 147 err.strerror += f’ Error loading “{dll}” or one of its dependencies.’ → 148 raise err 150 kernel32.SetErrorMode(prev\_error\_mode) 153 def \_preload\_cuda\_deps(lib\_folder, lib\_name): OSError: [WinError 126] The specified module could not be found. Error loading “C:\Users\aalek\anaconda3\Lib\site-packages\torch\lib\fbgemm.dll” or one of its dependencies. ---
**Author:** ![mahmutc](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mahmutc/32/64626_2.png) [@mahmutc](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmahmutc)%5C **Post date:** [August 22, 2024, 7:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcant-import-pipeline-from-transformers%2F103365%2F2 "2024-08-22T07:22:47Z")
If you haven’t seen yet, please check [Failed to import pytorch fbgemm.dll or one of its dependencies is missing - windows - PyTorch Forums](https://discuss.pytorch.org/t/failed-to-import-pytorch-fbgemm-dll-or-one-of-its-dependencies-is-missing/201969).