Venue: Wildt’sche Haus
Time: September 20th, between 1:00 PM - 6:30 PM
1:00 PM - 1:30 PM: Welcome coffee
1:30 AM - 2:30 AM: Intro to large language models
2:30 AM - 2:45 AM: Break
2:45 AM - 3:15 AM: Intro to Huggingface
3:15 AM - 4:00 PM: Exercise 1 - Predicting health perception
4:00 PM - 4:30 PM: Break
4:30 PM - 5:15 PM: Exercise 2 - Predicting personality structure
5:15 PM - 6:00 PM: Exercise 3 - Predicting cognitive reflection
6:00 PM - 6:30 PM: Discussion
There are two options for setting up your Python environment: (i) Google Colab (cloud-based), (ii) Locally. For the purposes of this workshop, we recommend using Golab due to the ease of setup and the availability of GPUs. However, if you would like to use your own machine, we also provide instructions for setting up your environment locally.
In the top-left, click New > More > Colaboratory. If you do not see Colaboratory, you may need to click “Connect more apps”, search for ‘Colaboratory’, and install it. Then click New > More > Colaboratory.
shift + enter) of your notebook to mount your Google Drive to the Colab environment. A pop-up will ask you to connect, click through the steps to connect your Google Drive to Colab (you will have to do this every time you open a new notebook).
from google.colab import drive drive.mount("/content/drive")
%cd /content/drive/MyDrive !git clone https://github.com/cdsbasel/LLM4behavior_workshop.git
conda create --name LLM4behavior_workshop python=3.8
The terminal will ask you to confirm the installation. Type “y” and press enter (do the same for any subsequent steps).
conda activate LLM4behavior_workshop
conda install -c huggingface -c conda-forge jupyter pandas numpy scikit-learn transformers datasets accelerate
pip install evaluate
pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu
If you are using Windows or Linux, please follow the instructions at https://pytorch.org/get-started/locally/ to install the appropriate version of PyTorch for your system.
You are now ready to start the exercises!