Umar Jamil

Videos

  • Building a distributed training framework from first principles
  • Flash Attention derived and coded from first principles with Triton (Python)
  • Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation
  • ML Interpretability: feature visualization, adversarial example, interp. for language models
  • Kolmogorov-Arnold Networks: MLP vs KAN, Math, B-Splines, Universal Approximation Theorem
  • Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math
  • Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.
  • Mamba and S4 Explained: Architecture, Parallel Scan, Kernel Fusion, Recurrent, Convolution, Math
  • Mistral / Mixtral Explained: Sliding Window Attention, Sparse Mixture of Experts, Rolling Buffer
  • Distributed Data Parallel (DDP) with PyTorch: complete tutorial with cloud infrastructure and code
  • Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware Training
  • Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)
  • BERT explained: Training, Inference, BERT vs GPT/LLamA, Fine tuning, [CLS] token
  • Coding Stable Diffusion from scratch in PyTorch
  • Coding LLaMA 2 from scratch in PyTorch - KV Cache, Grouped Query Attention, Rotary PE, RMSNorm
  • LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU
  • Segment Anything - Model explanation with code
  • LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch
  • LongNet: Scaling Transformers to 1,000,000,000 tokens: Python Code + Explanation
  • How diffusion models work - explanation and code!
  • Variational Autoencoder - Model, ELBO, loss function and maths explained easily!
  • Attention is all you need (Transformer) - Model explanation (including math), Inference and Training
  • Coding a Transformer from scratch on PyTorch, with full explanation, training and inference.
  • CLIP - Paper explanation (training and inference)

Umar Jamil

  • Umar Jamil
  • hkproj
  • ujamil
  • hkproj
  • @umarjamilai

ML Engineer and Researcher