Karthikeyan DhanakottiTokenization and Subword Tokenization in Generative AI: A Complete GuideIntroduction to Tokenization5d ago5d ago
Karthikeyan DhanakottiUnlocking Efficiency and Scale: The Mixture of Experts (MoE) and Sparse MoE (SMoE) Architectures…Think of a hospital with a team of specialist doctors — each doctor is an expert in a different area, such as cardiology, neurology, or…Aug 24Aug 24
Karthikeyan DhanakottiinData Science at MicrosoftExploring quantization in Large Language Models (LLMs): Concepts and techniquesLarge Language Models (LLMs) such as GPT have transformed natural language processing (NLP), with GPT-3 featuring an impressive 175 billion…Aug 20Aug 20
Karthikeyan DhanakottiRAGAS for RAG in LLMs: A Comprehensive Guide to Evaluation Metrics.IntroductionAug 15Aug 15
Karthikeyan DhanakottiBoosting Retrieval in RAG for LLMs: The Power of BM25 and RRFBM25 (Best Matching 25) and RRF (Reciprocal Rank Fusion) are two techniques that can be used to imBM25 (Best Matching 25) and RRF…Aug 11Aug 11
Karthikeyan DhanakottiStandardization and Min-Max Scaling in Machine Learning and Deep Learning.IntroductionAug 11Aug 11
Karthikeyan DhanakottiRisks Associated with Prompt Engineering in Large Language Models (LLMs)Prompt engineering in Large Language Models (LLMs) involves carefully crafting input prompts to guide the model’s output in a desired…Aug 9Aug 9
Karthikeyan DhanakottiUnderstanding Retrieval Augmented Generation (RAG) in Large Language ModelsWhat is Retrieval Augmented Generation (RAG)?Aug 3Aug 3
Karthikeyan DhanakottiEvaluating Distributional Differences: One-Sample vs Two-Sample Kolmogorov-Smirnov TestsKolmogorov-Smirnov Test (KS Test)Jul 20Jul 20
