Positional EncodingWhere Am I? This is the second part of our Transformer series blog, where we will deep dive into a topic called positional embedding. In this part, we’ll see what PE is and the types of PEs. Background Classical NLP and text generation used sequence-...Sep 12, 2025 · 4 min read1bytenand.hashnode.dev
BazarAI AgentAs always, I am late to the party… I wanted to experiment with the agentic capacity of language models. The last time I used an agent was when I built the RAG from scratch. We used a search tool to build, but it was not free (Google serpAPI 🤧), so I...Aug 3, 2025 · 4 min read1bytenand.hashnode.dev
KV cache in transformers“This will be a small experiment”. My thoughts as I started working on it a month ago. It is a simple concept of caching previous results for future calculations, similar to dynamic programming in DSA. I could not have been far from the truth. Well, ...Jul 24, 2025 · 3 min read1bytenand.hashnode.dev
CI/CD with GitHub Actions and Google CloudIn this era of AI copilots like GPT and Gemini, I decided — for reasons even I don’t fully understand — to build a CI/CD pipeline the old way: just me, Google, and a sea of Stack Overflow tabs. And somewhere between cryptic errors and outdated docs, ...Jul 1, 2025 · 7 min read1bytenand.hashnode.dev
Google search with LLMRecently in the world of Large Language Models like GPT, Gemini we have been hearing a word called Hallucination. It refers to a state where the LLM starts generating output that is factually incorrect. To solve this problem, the ML community invente...May 1, 2024 · 4 min read1bytenand.hashnode.dev
