Incorrect response of the pipeline/feature-extraction endpoint for the bloom model

I’ve used this as reference to extract embeddings using the bigscience/bloom models.
Using the url: the response is correct, returning a list of arrays. However when trying the bigscience/bloom model using the same request:, the response is [{'generated_text': '...'}] which appears to be a text-generation response.

Given the size of the model, I cannot check locally if the issue is with the model or the api endpoint. According to the documentation, both models should behave the same way as far as I can tell:
I think this is undesired behavior from this endpoint?