Fine-Tuning Generative Models
Go beyond basic prompting by training or fine-tuning generative models on your own data. Create custom AI models that replicate a specific artistic style or generate niche content using techniques like LoRA.
17 courses
Learn the fundamentals of 3D CAD design, part modeling, and assembly creation in CATIA V5, perfect for aspiring mechanical engineers and product designers.
Master the essentials of high-quality surface creation and parametric wireframe design in Catia for modern engineering projects.
Master surface modeling techniques in CATIA to design complex, aerodynamic, and aesthetic shapes using step-by-step written tutorials.
Learn how to configure key Confluence administrator settings, manage system permissions, and optimize platform performance through clear written guides.
Master model customization on Bedrock to adapt foundation models to your domain using fine-tuning, continued pre-training, and model distillation.
Learn to pre-train and fine-tune efficient ELECTRA language models using modern NLP libraries to solve real-world text classification and understanding tasks.
Learn to systematically search, validate, and optimize machine learning hyperparameters to build highly accurate and robust predictive models.
Learn to prepare datasets, train custom language models, and deploy specialized AI behavior for your applications using the OpenAI API.
Learn how to adjust temperature, top-p, and penalties to precisely guide the creativity, predictability, and structure of text generation models.
Understand the core concepts behind large language models, prompt engineering, and generative AI to confidently build your foundational knowledge.
Learn how to adapt pre-trained models to your specific tasks using modern fine-tuning techniques, dataset preparation strategies, and practical evaluation methods.
Build a clear understanding of what fine-tuning generative models actually means, when it is the right choice, and how techniques like LoRA fit in.
Walk through a practical workflow for fine-tuning generative models with LoRA and Dreambooth, from dataset preparation to evaluation and iteration.
Learn to systematically measure, compare, and optimize machine learning models using modern benchmarking techniques and evaluation metrics for reliable deployment.
Develop the longer-horizon practice of building a personal portfolio supported by custom fine-tuned generative models you can use, share, and evolve.
Learn practical strategies to train highly accurate computer vision models by balancing datasets, avoiding overfitting, and applying modern evaluation techniques.
Learn how to customize pre-trained text-to-image models using parameter-efficient fine-tuning techniques to generate high-quality, domain-specific visual assets.