Sergei Savvov – Medium

Sergei Savvov

Merge Large Language Models

Combine Mistral, WizardMath and CodeLlama in one model!

Jan 22

Merge Large Language Models

Jan 22

Published in
Towards Data Science

All you need to know to Develop using Large Language Models

Explaining in simple terms the core technologies required to start developing LLM-based applications.

Nov 15, 2023

All you need to know to Develop using Large Language Models

Nov 15, 2023

Published in
Better Programming

Hack Your Next Interview with Generative AI

Exploring the Future of AI: Crafting a Conceptual Interview Assistant Using Whisper and ChatGPT.

Oct 3, 2023

Hack Your Next Interview with Generative AI

Oct 3, 2023

Published in
Better Programming

Detecting LLM-Generated Texts

Is it possible to differentiate between what is written by a large language model and a human?

Sep 13, 2023

Detecting LLM-Generated Texts

Sep 13, 2023

Published in
Better Programming

Fixing Hallucinations in LLMs

Why LLMs hallucinate, approaches for mitigation, challenges with evaluation datasets, and more

Aug 28, 2023

Fixing Hallucinations in LLMs

Aug 28, 2023

Published in
Better Programming

You don’t need hosted LLMs, do you?

A comparison of self-hosted LLMs and OpenAI: cost, text generation quality, development speed, and privacy.

Aug 19, 2023

You don’t need hosted LLMs, do you?

Aug 19, 2023

Published in
Better Programming

7 Frameworks for Serving LLMs

Finally, a comprehensive guide into LLMs inference and serving with detailed comparison.

Aug 11, 2023

7 Frameworks for Serving LLMs

Aug 11, 2023

Published in
Better Programming

LLaMA 2: The Dawn of a New Era

Key differences from LLaMA 1, safety & violations, Ghost Attention and model performance.

Jul 24, 2023

LLaMA 2: The Dawn of a New Era

Jul 24, 2023

Published in
Better Programming

Create a Clone of Yourself With a Fine-tuned LLM

Unleash your digital twin

Jul 27, 2023

Create a Clone of Yourself With a Fine-tuned LLM

Jul 27, 2023

Published in
Better Programming

7 Ways to Speed Up Inference of Your Hosted LLMs

TLDR; techniques to speed up inference of LLMs to increase token generation speed and reduce memory consumption

Jun 26, 2023

7 Ways to Speed Up Inference of Your Hosted LLMs

Jun 26, 2023

Sergei Savvov

Sergei Savvov

I'm a Machine Learning Engineer, chemist, and nomad https://www.linkedin.com/in/sergey-savvov/

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams