Trelis Research

1:59

Quick Start Log OpenAI traces to Postgres

0:52

A Simple Postgres Logger for OpenAI Endpoints

18:39

A Simple Postgres Logger for OpenAI Endpoints - Open Source

0:34

Intro to TPU vs GPU

2:58

Unsloth or Transformers for fine tuning

33:45

TPU vs GPU

1:27

LLM Fine tuning Tips

1:56

What Open Weights Model should you Fine tune

1:46

How to Prepare Data for Fine tuning

1:47

Why fine tune

1:21:12

Fine tune Gemma 3, Qwen3, Llama 4, Phi 4 and Mistral Small with Unsloth and Transformers

38:14

Qwen3 Inference and MCP Agents

0:30

Qwen3 Inference and MCP Agents (Intro)

0:46

Approaches towards Solving ARC AGI

2:02:00

ARC Prize: A Guide to DSL, LLM-Guided & Test-time Training Approaches

0:34

Advanced Data Prep and Visualisation for Fine tuning LLMs

55:32

Advanced Data Prep and Visualisation Techniques for Fine-tuning LLMs

0:42

A Code Sandbox for Agents

15:49

Create a Python Sandbox for Agents to Run Code

0:25

Trelis Research Channel Updates - April 2025

10:06

April 2025 Channel Update - Repos, Grants, Collabs, and ARC AGI Team

0:33

Create Custom Benchmarks with YourBench and LightEval

0:20

Memory in LLMs is underappreciated

0:37

What LLM should I use for my application?

46:46

Build Custom LLM Benchmarks for your Application

0:42

Two ways data can leak in Cursor or Windsurf

0:43

Data Security Risks using Cursor and Windsurf

18:08

Is it safe to use Cursor or Windsurf?

0:43

Why building MCP Servers is Tricky!

0:40

How to Build and Publish an MCP Server

55:43

How to Build and Publish an MCP Server - A Detailed Guide

0:40

What should you use Qwen 2.5 Omni for?

0:28

Qwen 2.5 Omni

30:05

Qwen 2.5 Omni - The Most Multi-modal

2:01

How to use MCP with Cursor?

2:34

How to inspect an MCP server?

55:39

How does MCP work? How to use MCP?

0:52

How does MCP work? How to use MCP?

15:30

Price Comparison: OpenAI vs ElevenLabs vs DeepGram for TTS and STT

0:22

Voice Cloning with Sesame CSM-1B

2:23:10

Fine-tune Text to Speech Models in 2025: CSM-1B and Orpheus TTS

2:23:10

Diarization, Voice and Turn Detection

21:43

Gemma 3

1:02:57

Create and Fine-tune AI Avatar Videos

42:55

Document-Reading Agents with Read-Write Memory

30:20

Why use Keyword vs Vector Search?

48:46

Memory Management in LLMs and Agents

22:58

Train an LLM to Self-Correct with Verifiable Backtracking

55:15

SFT vs GRPO

32:44

How does GRPO work?

1:18:19

Reinforcement Learning for LLMs in 2025

11:27

The Best LLM? Google vs OpenAI, Anthropic and DeepSeek

1:11:20

Top Vision Models 2025: Qwen 2.5 VL, Moondream, & SmolVLM (Fine-Tuning & Benchmarks)

15:56

Run Distilled DeepSeek v3 Reasoning Models on Any Laptop with LMStudio

54:16

How to Boost RAG Accuracy with SmolAgents & BM25

14:08

OpenAI’s $500B ‘Stargate’ Project, GPU Export Bans, Musk’s Critique, and DeepSeek’s Reasoning Model

17:07

Channel Update - Playlists, Repos, Collabs, Grants, Memberships

49:45

Advanced Embedding Models and Techniques for RAG

33:21

Reasoning Models and Chinese Models

17:37

LiteLLM - One Unified API for for all LLMs

12:19

Nvidia RTX 5090 vs 4090, Project Digits & GB NVLink 72 at CES 2025

34:47

LLM Evals - Part 2: Improving Performance

1:01:57

How Deepseek v3 made Compute and Export Controls Less Relevant

34:23

LLM Evals - Part 1: Evaluating Performance

46:34

I Tested Every GPU

57:02

Serve Multiple LoRA Adapters on a Single GPU

1:17:56

Why Build Enterprise RAG with Postgres?

56:31

Multi modal Audio + Text Fine tuning and Inference with Qwen

1:00:38

How to Build an Inference Service

50:36

How to Fine-tune Florence 2: The Best Small Vision Model

24:23

Output Predictions - Faster Inference with OpenAI or vLLM

3:59

Coding Assistant for Jupyter Lab

25:09

Predicting Events with Large Language Models

34:44

Fine tune and Serve Faster Whisper Turbo

22:37

OpenAI Fine-tuning vs Distillation - Free Colab Notebook

1:17:59

Synthetic Data Generation and Fine tuning (OpenAI GPT4o or Llama 3)

1:00:00

Test Time Compute, Part 2: Verifiers

54:59

Test Time Compute, Part 1: Sampling and Chain of Thought

1:20:38

Distillation of Transformer Models

55:22

Fine tuning Pixtral - Multi-modal Vision and Text Model

39:40

Powering Gigawatt Data Centers

1:03:42

Full Fine tuning with Fewer GPUs - Galore, Optimizer Tricks, Adafactor

3:53

Make Cursor Understand Folder Structure - Coding with LLMs

45:52

Automated Prompt Engineering with DSPy

51:57

Fine Tune Flux Diffusion Models with Your Photos

40:40

How to use LLMs for Fact Checking

35:26

CONTEXT CACHING for Faster and Cheaper Inference

37:03

Run Speech-to-Speech Models on Mac or GPU

1:27:15

LLM Security 101: Jailbreaks, Prompt Injection Attacks, and Building Guards

2:56

Create an AI Assistant or Endpoint for your Documents

33:30

RAG - but with Verified Citations!

1:04:22

How to pick a GPU and Inference Engine?

1:19:44

LLM Tool Use - GPT4o-mini, Groq & Llama.cpp

1:15:44

Text to Speech Fine-tuning Tutorial

1:50:09

Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers

33:16

Improving LLM accuracy with Monte Carlo Tree Search

24:58

My TOP TEN TIPS for Fine-tuning

36:31

Preparing Fineweb - A Finely Cleaned Common Crawl Dataset

59:37

Data Preparation Tips and Tricks

35:45

Anonymizing Sensitive Data in LLM Prompts