Harsh GuptaDeep Dive into RAFT: Why Combining Approaches is KeyLarge Language Models (LLMs) have become increasingly adept at understanding and responding to human language. However, their performance…May 21May 21
Harsh GuptaRevolutionize Fine-Tuning: Reduce Training Time and Memory Usage with LoRAThe world of deep learning is witnessing an explosion in model size. Take large language models (LLMs) for instance — GPT-4 boasts a…May 9May 9
Harsh GuptaDemystifying the Central Limit Theorem: How Randomness Breeds NormalityImagine you run a bakery that makes muffins. The muffins aren’t identical; some come out slightly bigger, some smaller. This variation in…May 5May 5
Harsh GuptaIntuition behind Transformers: From Robots in Disguise to Revolutionizing AIForget the shapeshifting robots; in the realm of Artificial Intelligence (AI), transformers are a different breed altogether. They’re not…Apr 27Apr 27
Harsh GuptaDemystifying the Chatbot: A High-Level Look at LLM ArchitectureImagine a world where chatbots seamlessly understand your questions, respond with insightful answers, and even hold engaging conversations…Apr 4Apr 4
Harsh GuptaA Comprehensive Guide to Confidence IntervalsIn the realm of statistics, peering into the characteristics of a vast population often requires a closer look at a smaller, manageable…Mar 31Mar 31
Harsh GuptaIntuition Behind Linear TransformationsHey there! Linear transformations… sometimes they fly right over our heads in that first linear algebra course, right? Don’t worry, that’s…Mar 28Mar 28