Research - An Introduction to Text Analysis with Transformers and LLMs in Python
ConvolutionalTransformers Neuraland NetworksLarge Language Models (CNNs)LLMs) are widely used in avarious widetext varietyanalysis of applicationsapplications, such as imagetext classification, imagetext segmentation,generation, objectsummarisation, detection,translations, and image generation (with GAN).chatbots. In this course, you will learn how aTransformers CNNand worksLLMs work and how itthey can be practically applied into practicetext inclassification, imagetext classificationgeneration, and imagebuilding segmentation bychatbots using Python programming.
Objectives
Acquire the key competencies that are needed to use LLMs to do text classification, text generation and chatbots
Target audience
Any PhD students, post-docs, researchers of UNIL who would like to use LLMs in their research
Content
At the end of the course, the participants are expected to:
- Understand how Transformers and LLMs work
- Be able to use LLMs to do text classification, text generation and chatbots in Python
Length
1 day
Organization
Once per year
Location
In presential
Practicals
Prerequisites
- Basic knowledge of deep learning: we assume that you know how simple feedforward neural networks work, including how to interpret accuracy and loss curves (for example by attending the course "A Gentle Introduction to Deep Learning with Python and R").
- Be confortable with Python programming
IMPORTANT: To do the practicals
- On UNIL JupyterLab: You need to be able to access the eduroam wifi with your UNIL account or via the UNIL VPN
- On your laptop: No account requirement
- On Curnagl: Please register using your UNIL email address
- Note that in all cases you need to bring your own laptop