Trelis Research Courses

How to Avoid Going Out of Memory (OOM) in GPU Training

Master GPU memory management techniques to prevent out-of-memory errors during machine learning model training and fine-tuning processes.

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

Understanding TRM and HRM for Solving ARC Tasks and Machine Learning Applications

Explore TRM and HRM methodologies for solving ARC tasks and discover their broader applications in LLMs and machine learning systems.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

All About LoRA - Low-Rank Adaptation for Fine-Tuning Large Language Models

Discover LoRA fundamentals, hyperparameter selection, and practical fine-tuning techniques for efficient neural network adaptation in this comprehensive technical deep-dive.

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

GPT OSS Release - Inference and Fine-Tuning

Master OpenAI's new open-source models through hands-on inference setup, advanced fine-tuning techniques, and quantization methods for optimal performance.

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

ARC Prize 2025 Retrospective

Explore the ARC Prize 2025 competition through winner analysis, Trelis TRM fine-tuning methods, and firsthand competition insights in this comprehensive retrospective.

• YouTube
• 1 hour 38 minutes
• Self-Paced
• Free Video

Understanding Reasoning Models and Chinese AI Developments

Explore the evolution of AI reasoning models, focusing on breakthrough developments from Chinese labs and the technical mechanics behind reasoning traces and verification processes.

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

Advanced Embedding Models and Techniques for Retrieval Augmented Generation (RAG)

Master advanced embedding techniques for RAG systems, including ModernBERT implementation, contextual document embeddings, and practical fine-tuning strategies for optimal performance and efficiency.

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

Gemma 3 - Technical Overview and Performance Analysis

Explore Gemma 3's architecture, training methodology, and performance benchmarks, with insights on quantization, memory efficiency, and comparative analysis against other models like Quinn and Deep Seek.

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

Document-Reading Agents with Read-Write Memory

Explore how to build document-reading AI agents with read-write memory capabilities, including local memory setup, database integration, and effective search methods through practical demonstrations and code implementation.

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

Training Recursive Models - A Frontier in Adaptive Compute

Explore recursive neural network architectures that enable adaptive computation, efficient inference on smaller devices, and dynamic resource allocation for AI models.

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

Top Vision Language Models 2025 - Comparing Qwen 2.5 VL, Moondream, and SmolVLM

Dive into advanced vision language models with hands-on exploration of Qwen 2.5 VL, Moondream, and SmolVLM, covering fine-tuning techniques, performance benchmarking, and practical implementation strategies.

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

Comparing SFT and GRPO Methods for AI Model Fine-Tuning

Master advanced AI fine-tuning techniques through a detailed comparison of Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), including implementation strategies and practical applications.

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

Training LLMs to Self-Correct Using Verifiable Backtracking

Master advanced LLM training techniques with verifiable backtracking, budget forcing, and implementation strategies to enhance model self-correction capabilities and improve overall performance.

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

Running DeepSeek v3 Reasoning Models on Your Laptop - A Guide to LMStudio

Learn how to install, configure, and run DeepSeek v3 Reasoning Models efficiently on your laptop using LMStudio, with step-by-step guidance for different hardware configurations and performance optimization.

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

Build Custom LLM Benchmarks for Your Application

Learn to create and evaluate custom LLM benchmarks for your applications using tools like YourBench and LightEval, with practical demonstrations and advanced data generation techniques.

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