Let's reproduce GPT-2 (124M) [1hr Talk] Intro to Large Language Models Stable diffusion dreams of "blueberry spaghetti" for one night The spelled-out intro to language modeling: building makemore 2y | Andrej Karpathy Building makemore Part 2: MLP 2y | Andrej Karpathy Building makemore Part 3: Activations & Gradients, BatchNorm 2y | Andrej Karpathy Building makemore Part 4: Becoming a Backprop Ninja 2y | Andrej Karpathy Building makemore Part 5: Building a WaveNet 2y | Andrej Karpathy Let's build GPT: from scratch, in code, spelled out. 2y | Andrej Karpathy << < 1 2 Join group Members Search CreatedPast one dayPast four dayPast month Choose a GroupAndrej Karpathy Choose a User Sort byby relevanceUpvotedNew firstBookmark countComment count Search
![[1hr Talk] Intro to Large Language Models](https://www.cdn5.niftycent.com/d/e/a/7/0/B/g/1hr-talk-intro-to-large-language-models.webp "Stable diffusion dreams of \"blueberry spaghetti\" for one night")
