Fine tuning a GPT model that recommends nothing but AWS CDK
I'm going to take you on the journey of building a fine-tuned GPT model that answers technical questions with answers that exclusively recommend AWS CDK.
I'm going to take you on the journey of building a fine-tuned GPT model that answers technical questions with answers that exclusively recommend AWS CDK.
Learn how to generate tech jargon by taking trends from the ThoughtWorks technology radar and running sentences into DeepAI's text generator.
Building a Dog Bark Detector to help understand what my dogs do while I'm not home. In this post we cover the training and deployment of a Machine Learning module using the UrbanSound8K dataset.
Selfie2Anime was a successful use of Image-to-Image translation using UGATIT. In this post we learn how to setup a development environment capable of running UGATIT, then train out own variation of a model.
Learn how to use Conda environments to manage hundreds of different & varying python environments. Clean up your projects and make them more repeatable.
Generating Pokemon cards using a mixture of StyleGAN and RNN to create beautiful & vibrant cards ready for battle!
ICface is a generic face animator that is able to control the pose and expressions of a given face image. We explore how to use it for fun!
Automatic coloring and shading of Dune coloring book using manga-style lineart model from deepcolor. Making use of TensorFlow and CGAN
Containerising PyTorch models in a repeatable way. Deploy OpenAI's GPT-2 model and expose it over a Flask API. Finally deploy it to AWS Fargate container hosting using CloudFormation.
Generate Fake Facebook conversations using OpenAI's GPT-2 training model and a large number of your existing facebook message data. Perform training using Amazon SageMaker GPU instances and CloudFormation.
Generating Cat images using StyleGAN on AWS SageMaker. Developing a simple and repeatable Data Science pipeline for Generative Adversarial Network outputs.
Utilise Amazon SageMaker Ground Truth to offload manual data labelling to the Cloud or other members of your organisation.