Watch
The best AI, ML and programming videos. Tech only, no distractions.
15 videos from Umar Jamil✕ Clear
Building a distributed training framework from first principlesUmar Jamil · 50.3K views · 2 mo ago
Umar Jamil Live StreamUmar Jamil · 1 yr ago
Flash Attention derived and coded from first principles with Triton (Python)Umar Jamil · 108.7K views · 1 yr ago
Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanationUmar Jamil · 147.3K views · 2 yr ago
ML Interpretability: feature visualization, adversarial example, interp. for language modelsUmar Jamil · 13.1K views · 2 yr ago
Kolmogorov-Arnold Networks: MLP vs KAN, Math, B-Splines, Universal Approximation TheoremUmar Jamil · 41K views · 2 yr ago
Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, mathUmar Jamil · 40.6K views · 2 yr ago
Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.Umar Jamil · 79.2K views · 2 yr ago
Mamba and S4 Explained: Architecture, Parallel Scan, Kernel Fusion, Recurrent, Convolution, MathUmar Jamil · 68.7K views · 2 yr ago
Mistral / Mixtral Explained: Sliding Window Attention, Sparse Mixture of Experts, Rolling BufferUmar Jamil · 43.2K views · 2 yr ago
Distributed Data Parallel (DDP) with PyTorch: complete tutorial with cloud infrastructure and codeUmar Jamil · 42.8K views · 2 yr ago
Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware TrainingUmar Jamil · 62.3K views · 2 yr ago
Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)Umar Jamil · 92.3K views · 2 yr ago
BERT explained: Training, Inference, BERT vs GPT/LLamA, Fine tuning, [CLS] tokenUmar Jamil · 87.5K views · 3 yr ago
Coding Stable Diffusion from scratch in PyTorchUmar Jamil · 225.6K views · 3 yr agoKnow a great tech video? Suggest it