Umar Jamil
25.7K subscribers
48:46
Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math
Umar Jamil
3.9K views • 2 weeks ago
2:15:13
Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.
Umar Jamil
8.6K views • 2 months ago
1:14:29
Mamba and S4 Explained: Architecture, Parallel Scan, Kernel Fusion, Recurrent, Convolution, Math
Umar Jamil
28K views • 3 months ago
1:26:21
Mistral / Mixtral Explained: Sliding Window Attention, Sparse Mixture of Experts, Rolling Buffer
Umar Jamil
19K views • 4 months ago
1:12:53
Distributed Training with PyTorch: complete tutorial with cloud infrastructure and code
Umar Jamil
7.9K views • 4 months ago
50:55
Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware Training
Umar Jamil
10K views • 4 months ago
49:24
Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)
Umar Jamil
38K views • 5 months ago
54:52
BERT explained: Training, Inference, BERT vs GPT/LLamA, Fine tuning, [CLS] token
Umar Jamil
23K views • 6 months ago
5:03:32
Coding Stable Diffusion from scratch in PyTorch
Umar Jamil
72K views • 7 months ago
3:04:11
Coding LLaMA 2 from scratch in PyTorch - KV Cache, Grouped Query Attention, Rotary PE, RMSNorm
Umar Jamil
24K views • 7 months ago
1:10:55
LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU
Umar Jamil
41K views • 8 months ago
42:53
Segment Anything - Model explanation with code
Umar Jamil
12K views • 8 months ago
26:55
LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch
Umar Jamil
15K views • 9 months ago
29:58
LongNet: Scaling Transformers to 1,000,000,000 tokens: Python Code + Explanation
Umar Jamil
3.4K views • 9 months ago
21:12
How diffusion models work - explanation and code!
Umar Jamil
5.8K views • 9 months ago
27:12
Variational Autoencoder - Model, ELBO, loss function and maths explained easily!
Umar Jamil
14K views • 10 months ago
58:04
Attention is all you need (Transformer) - Model explanation (including math), Inference and Training
Umar Jamil
284K views • 11 months ago
2:59:24
Coding a Transformer from scratch on PyTorch, with full explanation, training and inference.
Umar Jamil
121K views • 11 months ago
14:01
CLIP - Paper explanation (training and inference)
Umar Jamil
3.1K views • 1 year ago
6:58
Wav2Lip (generate talking avatar videos) - Paper reading and explanation
Umar Jamil
2.1K views • 1 year ago
End of Videos