Lifelong Learning

Stay at the cutting edge of quantitative finance throughout your career

At the MLI we make Lifelong learning simple. At any point going forward all Alumni can access the next cohort. You will be able to join the new lectures live with the current crop of students.

Join the ML Institute (MLI) Lifelong Learning LinkedIn Group

This is for MLI Alumni only.

Thursday 7th March 2024:

Lifelong Learning, half day workshop: A Practical Guide to Customizing Large Language Models (LLMs) – Alexander Sokol

In this workshop, you will learn practical techniques for customizing LLMs for quant finance using prompt engineering, retrieval augmentation, and fine-tuning.

Prior knowledge of LLMs or Python programming not required. Open-source examples will be provided for those interested in running and modifying the code (CPU or GPU).

The workshop will include two 90-minute sessions (14:00 – 15:30 and 15:45 – 17:15) with 15 min coffee and Q&A breaks after each session.

Models: GPT-3.5, GPT-4, Llama 2, Code Llama

Session One: Prompting and Retrieval Augmentation – 14:00 to 15:30

Prompting – natural language programming of LLMs
- Principles of prompt engineering
- Prompt types
Retrieval augmentation – using information outside model training
- Embedding – asking questions over documents
- Chains – multi-step workflows
- Memory
Overcoming limitations
- Context window
- Large documents
- Hallucinations
- Reproducibility
Performance Optimization
- CPU and GPU performance profiles
- Quantization
Hands-on examples with Python
- Comprehension of trade confirmations

Q&A – 15:30 to 15:45

Session Two: Fine-Tuning – 15:45 to 17:15

Unsupervised fine-tuning
- Expanding the model dataset and vocabulary
Self-supervised fine-tuning
- Reducing prompt length
Supervised fine-tuning
- Generated datasets
- Curated datasets
Performance Optimization
- LORA and QLORA
Hands-on examples with Python
- Generation of draft model release notes

Q&A – 17:15 to 17:30

All MLI Alumni will be sent a password protected webinar link for this event.

Alexander Sokol:

Executive Chairman and Head of Quant Research, CompatibL

Alexander Sokol: Executive Chairman and Head of Quant Research, CompatibL

Alexander Sokol is the founder, Executive Chairman, and Head of Quant Research at CompatibL, a trading and risk technology company. He is also the co-founder of Numerix, where he served as CTO from 1996 to 2003, and the co-founder of Duality Group, where he served as CTO from 2017 to 2020.

Alexander won the Quant of the Year Award in 2018 together with Leif Andersen and Michael Pykhtin, for their joint work revealing the true scale of the settlement gap risk that remains even in the presence of initial margin. Alexander’s other notable research contributions include systemic wrong-way risk (with Michael Pykhtin, Risk Magazine), joint measure models, and the local price of risk (with John Hull and Alan White, Risk Magazine), and mean reversion skew (Risk Books, 2014).

Alexander earned his BA from the Moscow Institute of Physics and Technology at the age of 18, and a PhD from the L. D. Landau Institute for Theoretical Physics at the age of 22. He was the winner of the USSR Academy of Sciences Medal for Best Student Research of the Year in 1988.