We start by deploying Mistral 7B, a cutting-edge open-source LLM, onto a SageMaker endpoint. Following this, we work with the Reuters dataset, a Hugging Face dataset comprising 20,000 news articles. We break down these articles into smaller sections and apply bge-small, a compact open-source embedding model, to them. Next, we proceed to index these sections into an Amazon OpenSearch Serverless vector index, which we then query through LangChain. Additionally, aside from the RAG demonstration, we delve into some vital yet often overlooked steps related to authentication and security for OpenSearch Serverless.

SIn this video, I’ll guide you through the process of creating a Retrieval-Augmented Generation (RAG) chatbot using open-source tools and AWS services, such as LangChain, Hugging Face, FAISS, Amazon SageMaker, and Amazon TextTract. We begin by working with PDF files in the Energy domain. Our first step involves leveraging…

In this video, I delve into optimizing the fine-tuning of a Google FLAN-T5 model for legal text summarization. The focus is on employing QLoRA for parameter-efficient fine-tuning: all it takes is a few extra lines of simple code in your existing script. This methodology allows us to train the model with remarkable cost efficiency, utilizing even modest GPU instances, which I demonstrate on AWS with Amazon SageMaker. Tune in for a detailed exploration of the technical nuances behind this process.

Fine-tuning large language models doesn’t have to be complicated and expensive. In this tutorial, I provide a step-by-step demonstration of the fine-tuning process for a LLaMA 2 7-billion parameter model. Thanks to LoRA, 4-bit quantization and a modest AWS GPU instance (g5.xlarge), total cost is just a fistful of dollars 🤠 🤠 🤠

Fine-tuning large models doesn’t have to be complicated and expensive. In this tutorial, I provide a step-by-step demonstration of the fine-tuning process for a Stable Diffusion model geared towards Pokemon image generation. Utilizing a pre-existing script sourced from the Hugging Face diffusers library, the configuration is set to leverage the LoRA algorithm from the Hugging Face PEFT library. The training procedure is executed on a modest AWS GPU instance (g4dn.xlarge), optimizing cost-effectiveness through the utilization of EC2 Spot Instances, resulting in a total cost as low as $1.

In this video, I show you how to deploy Hugging Face models in one click on Azure, thanks to the model catalog in Azure ML Studio. Then, I run a small Python example to predict with the model. To get started, you simply need to navigate to the Azure ML Studio website and open the model catalog. Then, you can click on a model to select it. This will initiate the setup process, which takes care of all the required infrastructure for you. Once the setup is complete, Azure ML Studio provides a sample program and you can start testing the model immediately!

Experimenting with the latest and greatest models doesn’t have to be difficult. With SageMaker JumpStart, you can easily access and experiment with cutting-edge large language models without the hassle of setting up complex infrastructure or writing deployment code. All it takes is a single click. In this particular video, I…

In this video, I show you how to accelerate Stable Diffusion and Stable Diffusion XL inference with the Hugging Face Optimum Neuron library and AWS Inferentia 2. A few lines of code is all it takes, and of course, we run some benchmarks.

In this video, I compare the cost/performance of AWS Trainium with the NVIDIA V100 GPU. I first launch a trn1.32xlarge instance (16 Trainium chips) and a p3dn.24xlarge (8 V100s). Then, I run 3 benchmarks: language pretraining with GPT2, token classification with BERT Large, and image classification with the Vision Transformer. The results? Trainium is 2 to 5x faster, and 3 to 8x cheaper!