Sam Witteveen Courses

Llama 3.2 - Multimodal and Edge Computing Advancements

Explore Llama 3.2's multimodal capabilities, edge computing potential, and performance benchmarks. Learn about its vision-tuned models, lightweight versions, and integration with Ollama.

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

Fine-Tuning Palm 2 and Creating Datasets - How-To Guide

Learn to fine-tune Palm 2 models and create custom datasets for improved AI performance. Explore Vertex AI, dataset creation, and model tuning techniques.

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

Claude 3 Models Comparison: Opus, Sonnet, and Haiku - Performance and Features

Explore Claude 3's new models, comparing capabilities and performance through demos and benchmarks. Gain insights into Anthropic's latest AI advancements and their practical applications.

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

Exploring Gemini 1.5 Pro: Large Context Window and Multimodal Capabilities

Explore Gemini 1.5's capabilities with a 1 million token context window through demos on document querying, code writing, and multimodal processing of video and images.

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

Image Annotation with LLaVA and Ollama

Learn to annotate images using LLava 1.6 and Ollama. Explore file handling, image loading, API integration, and data management in this practical tutorial on building an image captioning application.

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

InternLM - A Strong Agentic Model for Math, Reasoning, and Function Calling

Explore InternLM: A powerful language model excelling in math, reasoning, and function calling. Learn its features, implementation, and local deployment options.

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

Google's New Approach to AI Agents - Analysis and Implications

Explore Google's innovative approach to AI agents, their unique features, and implications for developers in building advanced, multi-step AI assistants.

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

Google's Expansion of Gemini: New Features and Integrations - Google I/O 2024 Highlights

Explore Google's Gemini expansion: new app, advanced features, 1.5 Pro model with 2M token context, integration in Workspace, and innovative tools like NotebookLM and context caching.

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

Gemini 1.5 Pro for Code - Building LLM Agents with CrewAI

Explore Gemini 1.5 Pro's code capabilities through CrewAI, a framework for building AI agent systems. Learn to create and run multi-agent bots, integrate Gemini models, and leverage search tools.

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

Mistral Large with Function Calling - Review and Implementation

Explore Mistral Large's capabilities, benchmarks, and function calling through code examples and comparisons with Mistral Medium, showcasing its potential for advanced language tasks.

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

Creating an AI Agent with LangGraph, Llama 3, and Groq - Advanced Tutorial

Learn to create an advanced AI agent using LangGraph, Llama 3, and Groq. Explore key concepts, workflow, and implementation steps for building sophisticated language models and graph-based agents.

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

5 Common Problems in Building LLM Agents for Production

Explore common challenges in LLM Agent production: reliability, loops, tools, self-checking, and explainability. Gain insights on overcoming these hurdles for successful implementation.

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

Mastering Custom Tools for LLMs: Enhancing AI Agent Functionality

Explore custom tools for AI agents, enhancing functionality and building effective LLM agents. Learn tool categories, implementation strategies, and best practices for optimal performance.

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

Introducing Swarm: OpenAI's Groundbreaking Agent Framework with Code Examples

Explore OpenAI's Swarm framework through code examples, learning concepts and applications for multi-agent systems. Gain insights into routines, agent handoffs, context injection, and function calling.

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

Claude 3 Haiku Crash Course - Prompt Engineering and Multimodal Applications

Explore Claude 3 Haiku's capabilities through hands-on coding examples, covering text processing, JSON handling, multimodal tasks, and integration with LangChain for efficient AI development.

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