Shrinivasan SankarComparing Kolmogorov-Arnold Network(KAN ) and Multi-Layer Perceptrons (MLPs)We have taken the classic Multi-Layer Perceptrons (MLPs) for granted and built so many architectures around it. MLPs are part and parcel of…9 min read·1 day ago----
Shrinivasan SankarXLSTM — Extended Long Short-Term Memory NetworksLSTMs or Long Short-Term Memory Networks have been around for a long time. They have been applied for quite a few sequence-related tasks…8 min read·May 20, 2024----
Shrinivasan SankarinGoPenAIMake your LLM Fully Utilize the ContextA simple data-driven approach from Microsoft to increasing the context length of LLMs5 min read·May 9, 2024----
Shrinivasan SankarinLevel Up CodingChat with your emails with this RAG pipeline (LangChain + ChromaDB)Implement and run a simple application on your laptop to make LLMs chat with your emails in < 50 lines of code.6 min read·Mar 28, 2024----
Shrinivasan SankarinLevel Up CodingNaive Quantization Methods for LLMs — a hands-onImplementing Absolute max and zero point quantization helps learn advanced methods like GPTQ.4 min read·Mar 15, 2024----
Shrinivasan SankarinLevel Up CodingParameter Efficient Fine-tuning of the Gemma model on a single GPUA guide to fine-tuning the latest Gemma 2B model from Google with your in-house dataset on a single GPU.7 min read·Mar 5, 2024----
Shrinivasan SankarFine-tuning an LLM — The six-step lifecycleFine-tuning is an art and a methodical process similar to software engineering. It is extremely simplified and portrayed as a cakewalk in…7 min read·Feb 23, 2024----
Shrinivasan SankarRetrieval Augmented Generation(RAG) — A quick and comprehensive introductionIntroduction6 min read·Feb 13, 2024----
Shrinivasan SankarLumiere — The most promising Text-to-Video model yet from GoogleU-Net architecture modified to a space-time architecture coupled with MultiDiffusion is Lumiere7 min read·Feb 1, 2024----
Shrinivasan SankarYou will do one of these if you work in AI in 2024AI has come a long way ever since it took off in late 2016. Most people who worked in AI then were well-versed experts typically with a PhD…7 min read·Jan 15, 2024----