Niklas

Can you try what is explained here: https://github.com/Muennighoff/sgpt/issues/14#issuecomment-1352628910 You're likely using an old ST version

> I got the same error with the computing of the web interface at https://huggingface.co/bigscience-data/sgpt-bloom-1b7-nli a moment ago. Yes that's because the web interface is not using the latest ST...

Not sure about that; may be better to ask on the hugging face forums

it's the same for me: https://colab.research.google.com/drive/12bVqAKJKc7i5Bc5-7C963vnvKN7D_ZSb?usp=sharing

I think so; if you use mteb this issue is definitely no longer present as `DenseRetrievalParallelExactSearch` has been removed in favor of just doing the parallelism on the modeling side...

> When I run: `model = SentenceTransformer("Muennighoff/SGPT-125M-weightedmean-nli-bitfit")` the following error happens: `TypeError: Pooling.__init__() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'`. > > My machine: > > * OS: MacOs, chip M1...

> I am getting the same error. Installing sentence transformers from github does not help. Here's an example colab with it working for me: https://colab.research.google.com/drive/1xaYE3A1aNm3dwr_uvCBGk_XsS-wEqMI3?usp=sharing ``` !pip install git+https://github.com/UKPLab/sentence-transformers.git from...

You can check the location of the installation with `pip show sentence-transformers` & then modify the file `sentence_transformers/models/Pooling.py` to look exactly like https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/models/Pooling.py

> I downloaded the sentence-transformers locally and still reported the error: TypeError: **init**() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens' Can you try this https://github.com/Muennighoff/sgpt/issues/14#issuecomment-1405205453

There's no encoder_hidden_states for decoder-only models