AI Learning Center
Curated AI courses, tutorials, and guides from the world's best educators.
Parameter-Efficient Fine-Tuning (PEFT) for LLMs: A Hands-on Guide
Udemy
Master PEFT techniques like LoRA and Prompt Tuning to efficiently adapt large language models for various downstream tasks. Includes practical labs and case studies.
Practical RAG Implementation: From Embeddings to Generation
Pluralsight
Learn to build robust Retrieval Augmented Generation systems, covering embedding models, vector databases, and efficient retrieval strategies. Implement a complete RAG pipeline step-by-step.
Enterprise RAG with LangChain & LlamaIndex: Deployment Best Practices
O'Reilly
A hands-on workshop focused on building, scaling, and deploying RAG applications for production environments using leading frameworks. Covers advanced indexing and caching.
Zero to Production RAG with AWS & Azure Services
Coursera
Deploy scalable RAG systems on cloud platforms using services like Amazon SageMaker, Azure Cognitive Search, and OpenAI APIs. Covers infrastructure and MLOps.
Accelerating LLM Fine-tuning: QLoRA and Quantization Strategies
YouTube (Weights & Biases)
Dive deep into memory-efficient fine-tuning using QLoRA and other quantization techniques to train large models on consumer GPUs. Explores practical optimizations and tradeoffs.
Fine-tuning Multimodal LLMs: Vision and Language Integration
Stanford Online
Explore techniques for fine-tuning Large Multimodal Models (LMMs) for tasks combining vision and language. Delve into model architectures and dataset creation.
Fine-tuning LLMs with PyTorch Lightning and Hugging Face
GitHub
A comprehensive guide on leveraging PyTorch Lightning for efficient and scalable fine-tuning of Hugging Face Transformers. Covers best practices for distributed training.
Evaluating & Optimizing RAG Pipelines: Metrics and Tools
Towards Data Science
Understand key metrics for RAG performance and learn how to use specialized tools for evaluating retrieval accuracy and generation quality. Improve your RAG system iteratively.
Advanced Retrieval Strategies for RAG Systems
arXiv (Paper + Code)
Explore cutting-edge retrieval methods for RAG, including dense passage retrieval, re-ranking with cross-encoders, and query augmentation. Accompanied by open-source implementations.
Building Custom Instruction Datasets for LLM Fine-tuning
PwC AI Academy
Hands-on workshop to design, collect, and curate high-quality instruction datasets for effective fine-tuning of LLMs. Focuses on prompt engineering and data augmentation.
Domain-Specific LLM Adaptation: Fine-tuning for Niche Applications
DeepLearning.AI
Learn strategies for fine-tuning LLMs on custom datasets to achieve superior performance in specific domains. Focuses on data preparation, model selection, and evaluation.
Building Intelligent RAG Agents with Memory and Tools
YouTube (AI Explained)
Learn to design RAG systems that incorporate dynamic memory, tool usage, and multi-step reasoning for more sophisticated AI agents. Features practical examples.
Recommended Learning Paths
AI Beginner Path
- 1AI for Everyone
- 2Fast.ai Practical DL
- 3Prompt Engineering
LLM Engineer Path
- 1Deep Learning Spec
- 2Hugging Face NLP
- 3Building LLM Apps with LangChain
AI Agent Path
- 1LLM Engineering basics
- 2LangChain/LangGraph
- 3Multi-Agent Systems with CrewAI