Agus

As suggested by @alvarobartt we should work with the nvidia base images. I'll copy here the comments: - This should be enough to get started: ```Dockerfile FROM nvidia/cuda:12.3.0-base-ubuntu22.04 AS build...

Hi! @dvsrepo I have updated the [dataset with the sentiment](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-curation). I finally decided to use the `distilbert-base-uncased-finetuned-sst-2-english` model, it's more accurate and easy to detect the bad sentiment. The result...

Oh there seems to be an error with that one (and many of them...), I didn't noticed that sorry. This is how the sentiment score is computed: ```python from transformers...

I'll let the [paper](https://arxiv.org/pdf/2110.05719.pdf) for reference

Hi! When @kursathalat was adding one of the examples for the end2end task (https://github.com/argilla-io/argilla/issues/4183) we found that responses cannot be updated from the sdk. The `update_record` method is not showing...

Hi @nataliaElv! I think this really doesn't make sense, I saw we couldn't update this from the sdk (related to the #4328), but it doesn't make sense. I'll close this

Hi @kursathalat thanks for reviewing this! Please talk to @davidberenstein1957 to see the status of the metrics module.

Hi @kouyakamada, can you share the dataset you are testing from the hub so I can reproduce the error? I run the Pipeline with a small dataset of my own,...

Hi! Found the problem, is not related to the language 😄. The thing is, the dataset I was using for testing has 10 rows, yours 100, and the default `batch_size`...

Hi @bjoernpl in the next release this should be tackled: https://github.com/argilla-io/distilabel/pull/630