Cortex SearchCortex Search enables low-latency, high-quality “fuzzy” search over your Snowflake data.Sep 30Sep 30
LLMOps — Part 3 : Automation and Orchestration with PipelinesThis article is the continuation of the LLMOps series.May 2May 2
LLMOps — Part 2 : Data PreparationThis is the second part of my LLMOps series. In my previous article, we had briefly discussed about the workflow of LLMOps. The entire…Apr 27Apr 27
LLMOps — Part 1 : The IntroductionLLMOps is an extension of MLOps handling processes such as data preparation, model tuning, deployment, maintenance, monitoring etc.Apr 24Apr 24
A brief introduction to Knowledge GraphLet’s take an example of a virtual assistant. When you ask a question like “What is the capital of Canada ?”, the assistant will pull…Apr 13Apr 13
Mathematical intuition behind LoRA, QLoRALoRA is called Low Rank Adaptation of Large Language models and QLoRA is Quantised LoRA.Mar 7Mar 7
QuantisationIf you have read my previous article on Fine-tuning Llama2 using PEFT, then you must have come across a term called “Quantisation”.Feb 23Feb 23
Fine Tuning Llama 2 using PEFT techniquesA lot of open source LLM models like Llama2, Mistral, Falcon have been introduced recently. As we know from the full form of LLM that it…Feb 22Feb 22
Large Language ModelsWe all have seen the ‘autocomplete’ feature on our mobile phones. You just type a letter ‘H’, and then we get recommended words such as…May 29, 2023May 29, 2023