Heloisa Oss BollThe gradual information-fusing neural modelHello, this post is based on lecture 4 by Andrej Karpathy on building neural nets from scratch.Oct 23
InTowards Data SciencebyMatthew GuntonLine-By-Line, Let’s Reproduce GPT-2: Section 3 — TrainingThis blog post will go line-by-line through the code in Section 3 of Andrej Karpathy’s “Let’s reproduce GPT-2 (124M)”Sep 3
InTowards Data SciencebyMatthew GuntonLine-By-Line, Let’s Reproduce GPT-2: Section 2 — Hardware OptimizationThis blog post will go line-by-line through the hardware optimizations in Section 2 of Andrej Karpathy’s “Let’s reproduce GPT-2 (124M)”Jul 31Jul 31
Nate CodesSlopspicious: Drowning in AI SlopI was seriously pondering making AI write this for me, but I realized it would be too sloppy, and people would come to suspect me.Oct 18Oct 18
Tahir RaufImplementing a Character-Level Bigram Language Model Using N.N — Part 1BThis blog holds my notes of part2 of Andrej’s video of NN:ZeroToHero makemore series.Nov 30, 2023Nov 30, 2023
Heloisa Oss BollThe gradual information-fusing neural modelHello, this post is based on lecture 4 by Andrej Karpathy on building neural nets from scratch.Oct 23
InTowards Data SciencebyMatthew GuntonLine-By-Line, Let’s Reproduce GPT-2: Section 3 — TrainingThis blog post will go line-by-line through the code in Section 3 of Andrej Karpathy’s “Let’s reproduce GPT-2 (124M)”Sep 3
InTowards Data SciencebyMatthew GuntonLine-By-Line, Let’s Reproduce GPT-2: Section 2 — Hardware OptimizationThis blog post will go line-by-line through the hardware optimizations in Section 2 of Andrej Karpathy’s “Let’s reproduce GPT-2 (124M)”Jul 31
Nate CodesSlopspicious: Drowning in AI SlopI was seriously pondering making AI write this for me, but I realized it would be too sloppy, and people would come to suspect me.Oct 18
Tahir RaufImplementing a Character-Level Bigram Language Model Using N.N — Part 1BThis blog holds my notes of part2 of Andrej’s video of NN:ZeroToHero makemore series.Nov 30, 2023
Heloisa Oss BollFrom count-based to neural bigram modelsIn this post, I will summarize my notes from the 2nd lecture of the Zero to Hero course by Andrej Karpathy, which concerns building…Oct 8
Heloisa Oss BollBackpropagation, backed up by Andrej KarpathyI’ve been giving a shot at the free Neural Networks: Zero to Hero course by Karpathy on building neural networks, from scratch, in code.Oct 7
