Hello, I am trying to run this embedding model “sentence-transformers/LaBSE” with revision=“836121a0533e5664b21c7aacc5d22951f2b8b25b” on the Inference Endpoints. I have a result, but the embeddings numbers are different from the local execution. And not even correlated using cosine similarity. An…

Hi rpelissier :waving_hand: Sorry about the hassle here. I did a deep dive on issue and I think I know what’s going on: the model deployed in your inference endpoint uses the TEI server engine . Whereas the local example uses sentence-transformers. And unfortunately there’s a mismatch between the im…

Inference result not aligned with local version of same model and revision

Inference Endpoints on the Hub

rpelissier June 24, 2025, 2:13pm 5

Thank you John for helping.
I am not using this way of running an endpoint, I am using the no-code approach and the UI is showing the right model with the right version (screenshots).

1 Like

Topic		Replies	Views
Embedding endpoint returning [None] embeddings Inference Endpoints on the Hub	3	167	March 12, 2025
SentenceSimilarityInputsCheck expected dict not list: `__root__` in `parameters` Beginners	7	1886	August 11, 2023
Can one get embeddings from an inference API that computes Sentence Similarity (in 2023)? Inference Endpoints on the Hub	0	419	June 3, 2023
Integration Issue with Finetuned Embedding Inference Endpoint Inference Endpoints on the Hub	0	46	November 18, 2024
Calling Inference API for text embedding Inference Endpoints on the Hub	1	1875	August 4, 2023

Inference result not aligned with local version of same model and revision

Related topics