Lab 1 ModuleNotFoundError: No module named 'datasets'

Course Q&A Generative AI with Large Language Models
,
1

Week 1: Lab 1 - Generative AI Use Case: Summarize Dialogue

I followed the instruction to install the required packages to use PyTorch and Hugging Face transformers and datasets, using:

%pip install -U datasets==2.17.0 transformers==4.38.2 evaluate==0.4.0 rouge_score==0.1.2 peft==0.3.0 --quiet

I got message which has last two rows as below:

Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.12/site-packages (from python-dateutil>=2.8.2->pandas->datasets==2.17.0) (1.17.0)
Note: you may need to restart the kernel to use updated packages.

I tried to load the datasets with and without restarting kernel using

from datasets import load_dataset

I got error message:

Waiting for session 733a5b25-675e-4463-a9a4-4f459851c72c to get into ready status…
Session 733a5b25-675e-4463-a9a4-4f459851c72c has been created.
ModuleNotFoundError: No module named ‘datasets’

Can someone plz help with this? Thank you very much

1 Like
2

Restart the Kernel and run again all cells! When you are at the point of cell above, restart again the kernel and then run cells as normal after that!

Let us know again if you have still issues!

3

Dear @wei061lxw,

Have you run the following command
pip install datasets
before import
from datasets import load_dataset

If you still face problem, send me your notebook as DM.