praveenreddy_c·Jun 1My Understanding of Indexes in Vector Databases: Flat Index, ANN, HNSW, HFreshWhile creating my RAG playlist on my YouTube “Praveen Reddy Learnings”, I came to a topic: Indexing in Vector Databases.A response icon1A response icon1
praveenreddy_c·May 24My Understanding of vLLM and PagedAttentionI wish this is the last major topic I need to deeply understand in the LLM and fine-tuning space for this year, before I move back to…A response icon1A response icon1
praveenreddy_c·May 23Understanding KV Cache in LLM’sWe all know that Large Language Models (LLMs) are autoregressive models.A response icon1A response icon1
praveenreddy_c·May 17Understanding Classification Metrics in Machine Learning — Accuracy, Precision, Recall, F1 Score…Recently, I was working on a small fine tuning task using GCP Document AI. While evaluating the outputs, I suddenly realised I had…A response icon1A response icon1
praveenreddy_c·May 10Vision Transformer (ViT) — The Architecture Behind Modern Multimodal LLM’sWe all know how powerful the Transformer architecture has become in the NLP world. Models like GPT, BERT, and many other LLMs are all built…A response icon1A response icon1
praveenreddy_c·May 9Explanation of Q, K, V and Attention in Transformers Without Complex MathWe all know that Transformers are the reasons behind today’s powerful LLM’s. I had a little confusion around the Q, K, V concept in…A response icon3A response icon3
praveenreddy_c·May 3Direct Preference Optimization (DPO): A Simpler Alternative to RLHFI have written a blog on RLHF, which explains how we can fine-tune a pre-trained model. If you are not familiar with it, you can check it…A response icon1A response icon1
praveenreddy_c·May 2How LLMs Learn to Think: Inside DeepSeek’s GRPO TechniqueI first came across GRPO on LinkedIn and got a high-level understanding through ChatGPT. But later, I felt like diving deeper into the…A response icon1A response icon1
praveenreddy_c·May 1RLHF Explained: The Reason ChatGPT Responds Like a HumanI first came across RLHF(Reinforcement Learning with Human Feedback) on LinkedIn. When I went through the paper, one thing became very…A response icon1A response icon1
praveenreddy_c·Apr 13IA³ Fine-Tuning Explained — Infused Adapter by Inhibiting and Amplifying Inner ActivationsHey, In this blog, we will discuss IA³ fine-tuning, a parameter-efficient fine tuning method that the paper says IA³ performance is better…A response icon1A response icon1