Short course on Large Language Models for Physicists, Nov 6-8

[CMSP Seminars Secretariat]

This Wednesday afternoon ICOMP 
<https://www.ictp.it/home/consortium-scientific-computing> will host at 
ICTP the first lesson of a short course titled *Large Language Models 
for Physicists, *taught by Dr. Cristiano De Nobili. The course is 
designed for young researchers in applied/theoretical physics and 
climate science, who are interested in applying large language models 
(LLMs) in their research. All the interested postdocs and students are 
very welcome!

Below you can find more info.


*Short description of the  course*

To warm up, we will review the basics of deep learning and PyTorch. Then 
the Transformer architecture and its Self-attention Mechanism will be 
introduced and coded. A simple, small but complete autoregressive 
generative language model such as GPT-2 will be built. This will allow 
us to understand several relevant aspects of more sophisticated 
pre-trained LLMs, such as GPT4, Mistral or Llama. Afterwards, we will 
play with open-source pre-trained LLMs and, if possible, fine-tune one 
of them. In the last part of the course, we will explore some 
interesting, also from a physical point of view, emerging abilities of 
LLMs, touch upon multi-agent systems and their collective behaviour.


*Lecturer: *Cristiano De Nobili 
<https://www.linkedin.com/in/cristiano-de-nobili/>

*Schedule and rooms*
*
*
Wednesday  (6/11/24): 14.00 - 18.00, Giambiagi Lecture Room (Adriatico 
Guesthouse)
Thursday     (7/11/24):  9.00 - 13.00, Luigi Stasi Seminar Room 
(Leonardo Building)
Friday          (8/11/24):  9.00 - 13.00, Luigi Stasi Seminar Room 
(Leonardo Building)


Serafina Di Gioia
(Senior PostDoc, ICOMP)
https://www.ictp.it/home/consortium-scientific-computing