AI Bites Courses

Making LLMs Fully Utilize Context - A Data-Driven Approach

Discover how to enhance LLM context utilization through Microsoft's data-driven approach, exploring information-intensive training methods and practical solutions for improved context awareness and reasoning capabilities.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Optimizing LLM Pipelines with DsPy - Part 2

Dive into optimizing LLM pipelines by implementing multi-hop question-answering with DsPy framework, featuring Baleen pipeline and Bootstrap Few Shot algorithm optimization techniques.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

Introduction to DsPy Framework and Building Blocks - Part 1

Discover the fundamentals of DsPy framework for optimizing LLM pipelines, exploring its core components and how it differs from LangChain and LlamaIndex in this introductory guide.

• YouTube
• 20 minutes
• Self-Paced
• Free Video

Building a RAG Pipeline with LangChain and ChromaDB for Email-Based Chat Applications

Master practical RAG implementation with LangChain and ChromaDB to build an intelligent email-based chatbot system using vector stores, text splitters, and LLM integration.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

GGUF Quantization of Large Language Models Using LLAMA.cpp

Master GGUF quantization techniques to run large language models efficiently on personal devices using LLAMA.cpp, enabling GPU-free inference and deployment on laptops, phones, and watches.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

Simple Quantization of LLMs - A Hands-on Guide to Absolute Max and Zero Point Methods

Master practical LLM quantization techniques through hands-on implementation of Absolute Max and Zero Point methods, building foundational skills for advanced approaches like GPTQ and AWQ.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Getting Started with HuggingFace Transformers - Pipeline, Tokenizer, and Model Development

Master HuggingFace Transformers library fundamentals, from pipelines and tokenizers to models and Hub integration, enabling you to effectively work with and fine-tune Large Language Models.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Lumiere: Space-Time Diffusion Model for Text-to-Video Generation

Dive into Google's Lumiere text-to-video model, exploring its innovative space-time UNet architecture and MultiDiffusion design for creating temporally consistent video generation.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

ControlNet: Adding Conditional Control to Text-to-Image Diffusion Models

Delve into the groundbreaking ControlNet paper, exploring its architecture, classifier-free guidance, and spatial control capabilities in text-to-image diffusion models through detailed technical explanations.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

QLoRA: Efficient Training of Large Language Models Using Quantization and Low-Rank Adaptation

Discover how QLoRA enables efficient training of large language models on a single GPU through innovative techniques like NormalFloat, Double Quantization, and Paged Optimizers.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

LoRA: Low-Rank Adaptation for Parameter-Efficient Large Language Model Fine-Tuning

Discover how LoRA enables efficient fine-tuning of large language models through low-rank adaptation, from fundamental concepts to practical implementation in transformer architectures.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Stable Video Diffusion: Model Architecture and Training Pipeline

Dive into the technical architecture and training methodology of Stable Video Diffusion, exploring its three-stage process, data curation pipeline, and practical applications in AI-powered video generation.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Enhancing Image Generation Models Using Photogenic Needles in a Haystack - Meta's Emu Architecture

Dive into Meta's Emu architecture and quality fine-tuning process, exploring how this modified Latent Diffusion Model achieves exceptional image generation and precise editing capabilities.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

Mistral 7B - Understanding the Architecture and Performance Improvements

Dive into the technical innovations of Mistral 7B, exploring its groundbreaking attention mechanisms, caching strategies, and performance improvements over existing language models.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

LLaVA: Large Language and Vision Assistant - Understanding the First Instruction-Following Multimodal Model

Discover how LLaVA pioneered instruction-tuned multimodal AI, combining language and vision capabilities to create a groundbreaking Large Multimodal Model for advanced visual understanding and interaction.

• YouTube
• 11 minutes
• Self-Paced
• Free Video