Sergei SavvovMerge Large Language ModelsCombine Mistral, WizardMath and CodeLlama in one model!7 min read·Jan 22, 2024--4--4
Sergei SavvovinTowards Data ScienceAll you need to know to Develop using Large Language ModelsExplaining in simple terms the core technologies required to start developing LLM-based applications.12 min read·Nov 15, 2023--5--5
Sergei SavvovinBetter ProgrammingHack Your Next Interview with Generative AIExploring the Future of AI: Crafting a Conceptual Interview Assistant Using Whisper and ChatGPT.7 min read·Oct 3, 2023--4--4
Sergei SavvovinBetter ProgrammingDetecting LLM-Generated TextsIs it possible to differentiate between what is written by a large language model and a human?8 min read·Sep 13, 2023--5--5
Sergei SavvovinBetter ProgrammingFixing Hallucinations in LLMsWhy LLMs hallucinate, approaches for mitigation, challenges with evaluation datasets, and more9 min read·Aug 28, 2023--5--5
Sergei SavvovinBetter ProgrammingYou don’t need hosted LLMs, do you?A comparison of self-hosted LLMs and OpenAI: cost, text generation quality, development speed, and privacy.6 min read·Aug 19, 2023--20--20
Sergei SavvovinBetter Programming7 Frameworks for Serving LLMsFinally, a comprehensive guide into LLMs inference and serving with detailed comparison.14 min read·Aug 11, 2023--17--17
Sergei SavvovinBetter ProgrammingLLaMA 2: The Dawn of a New EraKey differences from LLaMA 1, safety & violations, Ghost Attention and model performance.6 min read·Jul 24, 2023--3--3
Sergei SavvovinBetter ProgrammingCreate a Clone of Yourself With a Fine-tuned LLMUnleash your digital twin11 min read·Jul 27, 2023--19--19
Sergei SavvovinBetter Programming7 Ways to Speed Up Inference of Your Hosted LLMsTLDR; techniques to speed up inference of LLMs to increase token generation speed and reduce memory consumption14 min read·Jun 26, 2023--2--2