46:20All about Sinusoidal Positional Encodings | What’s with the weird sin-cos formula?
A 46-minute video from Vizuara: “All about Sinusoidal Positional Encodings | What’s with the weird sin-cos formula?”.
232K subscribers on YouTube
Shorts, livestreams, trailers and promos are never listed. Unless a curator approved this channel in full, only individually picked videos appear.
46:20A 46-minute video from Vizuara: “All about Sinusoidal Positional Encodings | What’s with the weird sin-cos formula?”.
23:47A 24-minute video from Vizuara: “Build Deep Seek from Scratch 20 minute summary”.
15:16A 15-minute video from Vizuara: “Build DeepSeek from Scratch: Series Introduction”.
19:18A 19-minute video from Vizuara: “Build LLMs from scratch 20 minutes summary”.
54:11A 54-minute video from Vizuara: “Causal Attention Explained: Don't Peek into the Future!”.
48:04A 48-minute video from Vizuara: “Code Mixture of Experts (MoE) from Scratch in Python”.
40:59A 41-minute video from Vizuara: “Coding GPT-2 to predict the next token”.
49:39A 50-minute video from Vizuara: “Coding a fine-tuned LLM spam classification model | From Scratch”.
1:01:33A 62-minute video from Vizuara: “Coding the 124 million parameter GPT-2 model”.
43:21A 43-minute video from Vizuara: “Coding the entire LLM Pre-training Loop”.
45:06A 45-minute video from Vizuara: “Coding the entire LLM Transformer Block”.
34:44A 35-minute video from Vizuara: “Coding the model architecture for LLM classification fine-tuning”.
52:02A 52-minute video from Vizuara: “Data Batching in LLM instruction fine-tuning | Hands on project | Live Python coding”.
24:25A 24-minute video from Vizuara: “Dataloaders in Instruction Fine-tuning”.
31:03A 31-minute video from Vizuara: “Dataloaders in LLM Classification Finetuning | Python Coding | Hands on LLM project”.
39:57
58:36A 59-minute video from Vizuara: “Evaluating LLM performance on real dataset | Hands on project | Book data”.
52:58A 53-minute video from Vizuara: “Evaluating fine-tuned LLM using Ollama”.
27:57A 28-minute video from Vizuara: “GELU Activation Function in the LLM Architecture”.
37:56A 38-minute video from Vizuara: “GRPO Explained under 40 Minutes”.
31:57A 32-minute video from Vizuara: “How DeepSeek Rewrote Quantization Part 1 | Mixed Precision | Fine-grained quantization”.
21:51A 22-minute video from Vizuara: “How DeepSeek Rewrote Quantization Part 2 | Accumulation Precision | Online Quantization”.
1:04:15A 64-minute video from Vizuara: “How DeepSeek exactly implemented Latent Attention | MLA + RoPE”.
53:49A 54-minute video from Vizuara: “How DeepSeek rewrote Mixture of Experts (MoE)?”.
30:45A 31-minute video from Vizuara: “How DeepSeek rewrote Multi-Token Prediction (MTP)?”.
19:29A 19-minute video from Vizuara: “Instruction fine-tuning: Loading pre-trained LLM weights”.
36:41A 37-minute video from Vizuara: “Integer and Binary Positional Encodings | Journey towards Rotary Positional Encodings (RoPE)”.
27:24Intro
A 27-minute video from Vizuara: “Introduction to LLM Finetuning | Python Coding with hands-on-example”.
25:32Intro
A 26-minute video from Vizuara: “Introduction to LLM Instruction Fine-tuning | Loading Dataset | Alpaca Prompt format”.
20:25A 20-minute video from Vizuara: “Introduction to LLM Quantization”.
59:42A 60-minute video from Vizuara: “Key Value Cache from Scratch: The good side and the bad side”.
1:01:04A 61-minute video from Vizuara: “LLM Architecture in 1 hour | Journey of token through the LLM Architecture”.
23:47A 24-minute video from Vizuara: “LLM fine-tuning training loop | Coded from scratch”.
58:11A 58-minute video from Vizuara: “Lecture 1 - Deep Generative Modeling | Principles of Diffusion Models”.
49:04A 49-minute video from Vizuara: “Lecture 1 - Reasoning LLMs from Scratch - Series Introduction”.
52:15A 52-minute video from Vizuara: “Lecture 10 - Constructing Training Target for Flow Models | Principles of Diffusion Models”.