NandaKishore JoshiLLM Finetuning — An inside story (part 2)This series of articles is aimed at bringing out the practical aspects of successfully fine tuning a LLM on a real world use case at an…Aug 12Aug 12
NandaKishore JoshiLLM Finetuning — An Inside Story (Part 1)This series of articles is aimed at bringing out the practical aspects of successfully fine tuning a LLM on a real world use case at an…Aug 12Aug 12
NandaKishore JoshiWhen Retrieval Augmented Generation (RAG) Fails — Techniques to overcome limitations of RAGIn this article we try to explain the intricacies of RAG as a technique and there by understanding its limitations on enterprise use casesOct 23, 20232Oct 23, 20232
NandaKishore JoshiEmerging Architecture for Generative AI on Textual DataApplications of Generative AI are at the forefront post the LLM boom. This article helps you to use a LLM on custom documentAug 21, 2023Aug 21, 2023
NandaKishore JoshiWhat is TensorFlow Extended (TFX)?Google’s open source ML pipeline frameworkJul 29, 2022Jul 29, 2022
NandaKishore JoshiMulticlass Classification with Auto-Tuning CatBoostIn this article we will work on a Kaggle dataset of Date-fruits to classify them into 7 classes using Catboost and Hyperopt.May 26, 2022May 26, 2022
NandaKishore JoshiPart 2 : Evolutionary Algorithms for Reinforcement Learning — Solving OpenAI’s CartpoleSolving the Cartpole problem with a genetic algorithmApr 29, 2022Apr 29, 2022
NandaKishore JoshiPart 1 : Evolutionary Algorithms for Reinforcement Learning — An IntroductionIn this Article we deep dive to understand the working of Evolutionary algorithms & try to implement them to solve OpenAI’s cartpole…Apr 29, 2022Apr 29, 2022
NandaKishore JoshiPart 1 : Policy Based Reinforcement Learning — A Detailed StudyIn this article lets try to get a detailed understanding of what is On Policy and Off Policy Reinforcement Learning? What are the types of…Feb 26, 2022Feb 26, 2022
NandaKishore JoshiPart 2 : Policy Based Reinforcement Learning — OpenAI’s Cartpole with REINFORCE algorithmIn this article we will implement a policy based reinforcement learning algorithm called REINFORCE to solve OpenAI’s Cartpole problem.Feb 26, 2022Feb 26, 2022