Mirza SamadOptions to Deploy Your LLM (in increasing complexity):Amazon Bedrock API: If your LLM, such as LLAMA2–13B, is hosted on Amazon Bedrock, you’re set. Simply utilize it through an API without…Aug 28Aug 28
Mirza SamadOpen source Large Language Models in production on AWSDeploying a Language Model (LLM) at scale to efficiently serve a large number of users is a complex task that requires careful…Aug 27Aug 27
Mirza SamadFine-Tuning Large Language Models Using LoRA: (Must read before fine tuning)Fine-tuning large language models (LLMs) like GPT and BERT has become increasingly popular as these models are applied to diverse tasks…Aug 19Aug 19
Mirza SamadBuild your own Large Language Model (LLM) From Scratch Using PyTorchWhat will you achieve by the end of this post? You will be able to build and train a Large Language Model (LLM) by yourself while coding…Jun 20Jun 20
Mirza SamadFinetuning Llama-3 using ReFT (Representation Fine-Tuning) TechniqueIntroductionJun 2Jun 2
Mirza SamadPDF Talks: Using LangchainIn the dynamic landscape of digital communication, a trio of cutting-edge technologies — LangChain, LLM (Large Language Models), and GenAI…Feb 23Feb 23
Mirza SamadRun and test DynamoDB applications locally using Docker and Test containersDynamoDB Local is a version of Amazon DynamoDB that you can run locally as a Docker container (or other forms).Feb 23Feb 23