# Problem with Hugging face customised SQuad dataset
**URL:**
**Author:**  [@Aurelie123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAurelie123)%5C
**Post date:** [January 20, 2025, 3:40pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproblem-with-hugging-face-customised-squad-dataset%2F136560%2F1 "2025-01-20T15:40:25Z")
Hi,
I have created a custom dataset as csv file on a google sheet and the format is correct but when I uploaded it to hugging face the features answers says they are strings even though I copied exactly as per the original Squad dataset. In the original Squad dataset for the feature answers it says sequence and not strings like mine.
I wonder if anyone have ever came across this issues before ?
Thanks
Aurelie
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [January 20, 2025, 4:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproblem-with-hugging-face-customised-squad-dataset%2F136560%2F2 "2025-01-20T16:15:01Z")
Perhaps this?
> [@How to create dataset from CSV to training Question answering？](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-create-dataset-from-csv-to-training-question-answering%2F45851%2F4)%3A
>
> You should be able to parse the second pattern with: pd.read\_csv(..., converters={"answers": lambda x: json.loads(x)})
---
**Author:**  [@Aurelie123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAurelie123)%5C
**Post date:** [January 20, 2025, 5:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproblem-with-hugging-face-customised-squad-dataset%2F136560%2F3 "2025-01-20T17:17:38Z")
Thank you, I’ll have a look. I just uploaded the file to github where I saw the “” aka string elements, so right now I am removing by hand the “” and will download the file again from github as CSV and see if it works , if not I will try the other post .
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [January 20, 2025, 10:36pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproblem-with-hugging-face-customised-squad-dataset%2F136560%2F4 "2025-01-20T22:36:50Z")
As a last resort, you can specify the data format directly, but it would be better if it could be recognized automatically.
> **[Dataset features](https://huggingface.co/docs/datasets/about_dataset_features)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
---
**Author:**  [@Aurelie123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAurelie123)%5C
**Post date:** [January 21, 2025, 4:40pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fproblem-with-hugging-face-customised-squad-dataset%2F136560%2F5 "2025-01-21T16:40:53Z")
Thank you , very good I guess I will use that as I was unable to make the new CSV file working. It’s a bit odd that it’s being recognised as strings and not sequence but maybe that could be google sheets too and wasn’t sure how to make them a sequence in google sheet. Also I used a for loop to get the indexes and manually added them as at the moment i don’t have enough RAM on google colab unless i buy more which I might but for the sake of the small dataset I want to see if i can train it without more RAM. As regards to automatically update the csv file with a for loop , its not possible right now due to lack of RAM. It crashes half way.