Trelis Research Courses

Forecast Anything with Transformers - Chronos and PatchTST for Time Series Forecasting

Master time-series forecasting using transformer models like Chronos and PatchTST, including their architectures, implementation differences, and practical applications through hands-on demonstrations.

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

Serve a Text to Speech Model with vLLM

Discover how to deploy and serve the Orpheus Text-to-Speech model using vLLM with continuous batching, including setup, inference, and audio token decoding techniques.

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

Analyze GitHub Repos with Gitingest MCP

Master GitHub repository analysis using Gitingest MCP server to fetch summaries, folder structures, and content for enhanced code understanding and development workflows.

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

Professional Quality Voice Cloning - Open Source vs ElevenLabs

Master professional voice cloning techniques using open-source models like Sesame and Orpheus, comparing quality with ElevenLabs through hands-on fine-tuning and evaluation.

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

Building Enterprise RAG Systems with PostgreSQL - A Comprehensive Implementation Guide

Master enterprise-level RAG implementation using Postgres, covering vector search, BM25 optimization, document chunking, and performance tuning for efficient information retrieval and processing.

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

Building an Auto-scaling AI Inference Service - From Setup to Deployment

Master the fundamentals of building and scaling AI inference services, from GPU utilization to auto-scaling implementation, Docker configuration, and API endpoint setup for optimal performance.

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

Multimodal Audio and Text Fine-tuning with Qwen - Implementation Guide

Master multimodal audio and text processing using Qwen 2, from model architecture to practical implementation. Learn LoRA fine-tuning, data preparation, and deployment strategies for audio-text applications.

• YouTube
• 57 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

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

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

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

Distillation of Transformer Models - Tutorial and Code Walk-through

Learn advanced techniques for distilling transformer models, including pruning, fine-tuning, and performance evaluation. Gain practical insights through code walkthroughs and real-world examples.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Fine-tuning Pixtral - Multi-modal Vision and Text Model

Explore fine-tuning techniques for Pixtral, a multi-modal vision and text model. Learn about architecture, custom image encoding, dataset preparation, and advanced training strategies for improved performance.

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

Test Time Compute: Sampling and Chain of Thought Techniques

Explore advanced inference techniques like sampling and chain of thought to enhance AI model performance. Learn to optimize test-time compute for improved accuracy and efficiency.

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

Test Time Compute: Verifiers and Parallel Sampling - Part 2

Explore advanced inference techniques using verifiers, parallel sampling, and prompt optimization to enhance language model performance and accuracy.

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