16:01

Mixture of Transformers for Multi-modal foundation models (paper explained)

11:33

AI App to talk to your laptops locally (Local Alexa) - hands-on

08:52

LightRAG - A simple and fast RAG that beats GraphRAG? (paper explained)

07:26

How I generate unlimited AI images for free!

06:00

bitnet.cpp from Microsoft: Run LLMs locally on CPU! (hands-on)

06:43

The new claude 3.5 sonnet - computer use, benchmark and more

09:22

Introduction to PDF Parsing, challenges and methods (RAG Series)

12:33

Swarm from Open AI - routines, handoffs and agents explained with code

23:28

Meta Movie Gen Research Paper explained

18:00

Contextual Information Retrieval for improving your RAG pipeline (from Anthropic)

15:43

Qwen2.5 coder - Combines code generation with reasoning to build coding agents!

08:50

Qwen2.5 Math - world's leading open-source Math model?

09:01

Qwen 2.5 - The Small Language Model? (a quick look)

16:44

o1 preview from OpenAI is all about reasoning - A comprehensive look

15:22

Model Router - choose the right AI model using AI

14:21

Segment Anything 2 (SAM2) from Meta: The next generation of Meta Segment Anything Model for videos

17:29

Chunking in RAG (with hands-on in LangChain and LlamaIndex) - RAG video series

18:48

Claude3.5 Sonnet vs GPT4o (ChatGPT) - an honest review

22:30

Kolmogorov-Arnold Networks (KAN) - paper explained (maths, B-splines, experiments and KAN vs MLP)

14:14

XLSTM - Extended LSTMs with sLSTM and mLSTM (paper explained)

13:52

Make your LLMs fully utilize the context (paper explained)

55:41

Podcast #3 - Becoming a Kaggle GM + learning AI by OpenSource contribution...

21:16

Build a RAG app using LangFlow + @streamlitofficial with minimal coding | LangFlow crash course

55:18

Podcast #2 - Learning AI today, Cracking Kaggle Competitions, Java in Data Science ...

10:02

DsPy crash course - optimizing LLM pipelines with DsPy (part 2)

19:35

DsPy crash course - optimize your LLM pipelines with DsPy (Part 1)

18:07

Implementing RAG using @LangChain and ChromaDB. Chat with your emails with this pipeline!

12:10

GGUF quantization of LLMs with llama cpp

14:57

Simple quantization of LLMs - a hands-on

49:11

From MSc to Google Research - Songyou Peng (Episode #1 AI Bites Show)

24:11

Fine-tuning LLMs with PEFT and LoRA - Gemma model & HuggingFace dataset

09:21

fine tuning LLMs - the 6 stages

09:26

Retrieval Augmented Generation (RAG) explained

15:54

Get started with HuggingFace Transformers - Pipeline, Custom Pipeline, Tokenizer, Model, Hub

10:30

lumiere from google - A Space-Time Diffusion Model for Video Generation

14:03

Learn ML in 2024 - YouTube roadmap (100% free)

13:26

controlnet paper explained - Adding Conditional Control to Text-to-Image Diffusion Models

11:44

QLoRA paper explained (Efficient Finetuning of Quantized LLMs)

10:42

LoRA (Low-rank Adaption of AI Large Language Models) for fine-tuning LLM models

10:46

Gemini from Google - walkthrough in 10 mins

13:42

Stable Vidoe Diffusion - model architecture, training procedure and results (paper fully explained)

10:23

Emu from Meta (paper explained)

10:56

Mistral 7b - the best 7B model to date (paper explained)

10:45

LLaVA - the first instruction following multi-modal model (paper explained)

08:31

Autogen tutorial - next-generation LLM agents framework

09:56

NExT-GPT: The first Any-to-Any Multimodal LLM

13:04

Quantization in Deep Learning (LLMs)

10:28

Textbooks Are All You Need - phi-1.5 by Microsoft

11:43

LongNet: Scaling Transformers to 1B tokens (paper explained)

16:22

RT2 (Robotics Transformer 2) from DeepMind

16:25

LLAMA2 model demo - UI options without coding

11:21

LLAMA 2 paper explained - first free commercial model vs ChatGPT!

12:22

Orca LLM - bridging the gap between ChatGPT and opensource?!

13:15

MusicGen paper explained

09:50

Introduction to Prompt Engineering - prompts, types and formats

12:30

ImageBind paper explained: One Embedding Space To Bind Them All (from Meta AI)

11:59

DINOv2 from Meta AI: Data pipeline, model training and results explained

16:18

Segment Anything Model (SAM) from Meta AI: model architecture, data engine, results and limitations

07:57

What are AutoEncoders in deep learning? - explained

06:09

introduction to Generative AI Models | Generative AI