Umar Jamil
I'm a Machine Learning Engineer from Milan, Italy, teaching complex deep learning and machine learning concepts to my cat, 奥利奥.我也会一点中文.
- 48:46
- Ай бұрын
Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math
- 2:15:13
- 3 ай бұрын
Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.
- 1:14:29
- 4 ай бұрын
Mamba and S4 Explained: Architecture, Parallel Scan, Kernel Fusion, Recurrent, Convolution, Math
- 1:26:21
- 5 ай бұрын
Mistral / Mixtral Explained: Sliding Window Attention, Sparse Mixture of Experts, Rolling Buffer
- 1:12:53
- 5 ай бұрын
Distributed Training with PyTorch: complete tutorial with cloud infrastructure and code
- 50:55
- 5 ай бұрын
Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware Training
- 49:24
- 6 ай бұрын
Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)
- 5:03:32
- 8 ай бұрын
Coding Stable Diffusion from scratch in PyTorch
- 3:04:11
- 9 ай бұрын
Coding LLaMA 2 from scratch in PyTorch - KV Cache, Grouped Query Attention, Rotary PE, RMSNorm
- 1:10:55
- 9 ай бұрын
LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU
- 42:53
- 9 ай бұрын
Segment Anything - Model explanation with code
- 26:55
- 10 ай бұрын
LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch
- 21:12
- 10 ай бұрын
How diffusion models work - explanation and code!
- 58:04
- Жыл бұрын
Attention is all you need (Transformer) - Model explanation (including math), Inference and Training
- 2:59:24
- Жыл бұрын
Coding a Transformer from scratch on PyTorch, with full explanation, training and inference.
- 14:01
- Жыл бұрын
Пікірлер