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.

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

zeta-alpha-ai/Zeta-Alpha-E5-Mistral cannot be loaded #1655

Open
Muennighoff opened this issue Jan 1, 2025 · 4 comments
Open

zeta-alpha-ai/Zeta-Alpha-E5-Mistral cannot be loaded #1655

Muennighoff opened this issue Jan 1, 2025 · 4 comments

Comments

@Muennighoff
Copy link
Contributor

import mteb
mteb.get_model("zeta-alpha-ai/Zeta-Alpha-E5-Mistral")
WARNING:mteb.model_meta:Loader not specified for model zeta-alpha-ai/Zeta-Alpha-E5-Mistral, loading using sentence transformers.
/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_auth.py:104: UserWarning: 
Error while fetching `HF_TOKEN` secret value from your vault: 'Requesting secret HF_TOKEN timed out. Secrets can only be fetched when running from the Colab UI.'.
You are not authenticated with the Hugging Face Hub in this notebook.
If the error persists, please let us know by opening an issue on GitHub (https://github.com/huggingface/huggingface_hub/issues/new).
  warnings.warn(
modules.json: 100%
 349/349 [00:00<00:00, 19.4kB/s]
config_sentence_transformers.json: 100%
 195/195 [00:00<00:00, 9.80kB/s]
README.md: 100%
 157k/157k [00:00<00:00, 3.94MB/s]
sentence_bert_config.json: 100%
 54.0/54.0 [00:00<00:00, 3.31kB/s]
adapter_config.json: 100%
 741/741 [00:00<00:00, 23.1kB/s]
config.json: 100%
 683/683 [00:00<00:00, 21.6kB/s]
---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
[<ipython-input-2-2f54434973c0>](https://localhost:8080/#) in <cell line: 2>()
      1 import mteb
----> 2 mteb.get_model("zeta-alpha-ai/Zeta-Alpha-E5-Mistral")

9 frames
[/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py](https://localhost:8080/#) in from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, weights_only, *model_args, **kwargs)
   3927                                 )
   3928                             else:
-> 3929                                 raise EnvironmentError(
   3930                                     f"{pretrained_model_name_or_path} does not appear to have a file named"
   3931                                     f" {_add_variant(WEIGHTS_NAME, variant)}, {_add_variant(SAFE_WEIGHTS_NAME, variant)},"

OSError: intfloat/e5-mistral-7b-instruct does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt or flax_model.msgpack.
@Samoed
Copy link
Collaborator

Samoed commented Jan 1, 2025

I encountered the same error when trying to load it with sentence-transformers version v3.3.0, but it worked with v3.3.1.

@KennethEnevoldsen
Copy link
Contributor

should we disable sentence-transformers v3.3.0?

@Muennighoff
Copy link
Contributor Author

Hm I still get the issue in this example colab https://colab.research.google.com/drive/1TFby6CvgH8AIi_bhZ49szTxMqDjWMDo_?usp=sharing even with v3.3.1 🤔

@Samoed
Copy link
Collaborator

Samoed commented Jan 1, 2025

That's very strange. I tried loading it several times, and sometimes it works while other times it doesn't. I've created an issue to address this: https://huggingface.co/zeta-alpha-ai/Zeta-Alpha-E5-Mistral/discussions/3

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants