Submissions from github.com/karpathy

		Reproducing GPT-2 in llm.c (github.com/karpathy)
		618 points by tosh on May 28, 2024 \| past \| 117 comments
		Llm.c State of the Union (github.com/karpathy)
		1 point by neeleshs on May 4, 2024 \| past
		Layernorm (github.com/karpathy)
		3 points by sva_ on April 11, 2024 \| past
		Full forward pass of GPT-2 in one file of pure CUDA (github.com/karpathy)
		63 points by tosh on April 10, 2024 \| past \| 4 comments
		Llm.c – LLM training in simple, pure C/CUDA (github.com/karpathy)
		1050 points by tosh on April 8, 2024 \| past \| 168 comments
		Karpathy: SVM vs. K-NN on Embeddings (github.com/karpathy)
		1 point by skanderbm on Feb 24, 2024 \| past
		Code for the Byte Pair Encoding algorithm, commonly used in LLM tokenization (github.com/karpathy)
		81 points by magoghm on Feb 17, 2024 \| past \| 31 comments
		Karpathy removes llama licence from llama2.c (github.com/karpathy)
		3 points by orwellg1984 on July 26, 2023 \| past
		Llama2.c: Inference llama 2 in one file of pure C (github.com/karpathy)
		707 points by anjneymidha on July 23, 2023 \| past \| 165 comments
		KNN vs. SVM (github.com/karpathy)
		3 points by tosh on April 15, 2023 \| past
		Neural Networks: Zero to Hero (github.com/karpathy)
		1 point by greenSunglass on Jan 24, 2023 \| past
		NanoGPT (github.com/karpathy)
		1532 points by trekhleb on Jan 11, 2023 \| past \| 320 comments
		The simplest, fastest repository for training and fine-tuning medium-sized GPTs (github.com/karpathy)
		2 points by Terretta on Jan 10, 2023 \| past
		nanoGPT: The simplest repository for training medium-sized GPTs (github.com/karpathy)
		3 points by isoprophlex on Jan 3, 2023 \| past \| 1 comment
		Micrograd: A Tiny Autograd Engine (github.com/karpathy)
		3 points by memorable on Nov 4, 2022 \| past
		Neural Networks: Zero to Hero (github.com/karpathy)
		3 points by gzer0 on Sept 12, 2022 \| past
		An autoregressive character-level language model for making more things (github.com/karpathy)
		2 points by phsilva on Sept 8, 2022 \| past \| 1 comment
		MinGPT: Minimal PyTorch re-implementation of GPT (github.com/karpathy)
		223 points by memorable on Sept 6, 2022 \| past \| 24 comments
		ArXiv-sanity lite: get recommendations of similar papers (github.com/karpathy)
		3 points by ofou on March 28, 2022 \| past
		Pure Python from-scratch zero-dependency implementation of Bitcoin (github.com/karpathy)
		2 points by ofou on June 22, 2021 \| past
		Karpathy's MinGPT (github.com/karpathy)
		374 points by aliabd on Aug 17, 2020 \| past \| 102 comments
		A tiny scalar-valued autograd engine (github.com/karpathy)
		2 points by mooreds on April 26, 2020 \| past
		Micrograd: A tiny autograd engine (~50 LOC) and a neural net library (~60 LOC) (github.com/karpathy)
		3 points by sebg on April 17, 2020 \| past
		Karpathy/micrograd: A tiny autograd engine and a neural net library on top of it (github.com/karpathy)
		1 point by EvgeniyZh on April 14, 2020 \| past
		MicroGrad: A tiny autograd engine (~50 LOC) and neural net library on top of it (github.com/karpathy)
		2 points by RichardRNN on April 14, 2020 \| past
		Aspires to help the influx of bioRxiv / medRxiv papers on Covid-19 (github.com/karpathy)
		1 point by dennisy on March 30, 2020 \| past
		Find who you should follow on Twitter based on who the people you follow follows (github.com/karpathy)
		2 points by kumaranvpl on April 9, 2018 \| past
		Full RNN/LSTM implement under 600 lines no deps JS (github.com/karpathy)
		3 points by ghosthamlet on Nov 4, 2017 \| past
		Multi-layer RNN for character-level language models in Torch [GitHub] (github.com/karpathy)
		3 points by kiril-me on Jan 19, 2017 \| past
		Arxiv sanity preserver (github.com/karpathy)
		2 points by T-A on Feb 28, 2016 \| past
		More

HN For You