Medium

Aris Tsakpinis

In

TDS Archive

by

Aris Tsakpinis

·

Nov 8, 2024

Preference Alignment for Everyone!

Frugal RLHF with multi-adapter PPO on Amazon SageMaker

Preference Alignment for Everyone!

In

TDS Archive

by

Aris Tsakpinis

·

Jun 3, 2024

A Deep Dive into Fine-Tuning

Stepping out of the “comfort zone” — part 3/3 of a deep-dive into domain adaptation approaches for LLMs

A Deep Dive into Fine-Tuning

In

TDS Archive

by

Aris Tsakpinis

·

May 31, 2024

A Deep Dive into In-Context Learning

Stepping out of the “comfort zone” — part 2/3 of a deep-dive into domain adaptation approaches for LLMs

A Deep Dive into In-Context Learning

In

TDS Archive

by

Aris Tsakpinis

·

May 28, 2024

Introduction to Domain Adaptation- Motivation, Options, Tradeoffs

Stepping out of the “comfort zone” — part 1/3 of a deep-dive into domain adaptation approaches for LLMs

Introduction to Domain Adaptation- Motivation, Options, Tradeoffs

Aris Tsakpinis

·

May 21, 2024

LLM domain adaptation using continued pre-training — Part 4/4

Exploring domain adaptation via continued pre-training for large language models (LLMs)? This 4-part series answers the most common…

LLM domain adaptation using continued pre-training — Part 4/4

Aris Tsakpinis

·

May 21, 2024

LLM domain adaptation using continued pre-training — Part 2/4

Exploring domain adaptation via continued pre-training for large language models (LLMs)? This 4-part series answers the most common…

LLM domain adaptation using continued pre-training — Part 2/4

In

TDS Archive

by

Aris Tsakpinis

·

Sep 7, 2023

Leveraging qLoRA for Fine-Tuning of Task-Fine-Tuned Models Without Catastrophic Forgetting

Learn how to infuse knowledge into purpose-fine-tuned models while keeping their task-specific nature

Leveraging qLoRA for Fine-Tuning of Task-Fine-Tuned Models Without Catastrophic Forgetting

Aris Tsakpinis

·

Aug 29, 2023

Measuring and improving UX metrics of LLM-powered chatbots: latency benchmarking with LangChain…

What is this about and why is this relevant?

Measuring and improving UX metrics of LLM-powered chatbots: latency benchmarking with LangChain…

Aris Tsakpinis

Aris Tsakpinis

WW Lead GenAI Open-Source @ AWS - PhD candidate for ML Engineering @ University of Regensburg — All opinions are my own

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech