Skip to main content

AI Researcher Hub

GitHubkarpathy/nanoGPTAndrej Karpathy
YouTubeNeural Networks: Zero to HeroKarpathy
BlogThe Illustrated GPT-2Jay Alammar
PaperAttention Is All You NeedVaswani et al. 2017
GitHubrasbt/LLMs-from-scratchSebastian Raschka
BookBuild a Large Language Model (From Scratch)Raschka
GitHubunslothai/unslothUnsloth AI
GitHubmeta-llama/llamaMeta
GitHubopenai/whisperOpenAI
GitHubgoogle-deepmind/alphafoldDeepMind
GitHubdeepseek-ai/DeepSeek-R1DeepSeek
GitHubgoogle/gemma.cppGoogle
YouTubeTwo Minute PapersKároly Zsolnai-Fehér
YouTube3Blue1Brown — Neural networksGrant Sanderson
BlogThe Illustrated TransformerJay Alammar
PaperScaling Laws for Neural LMsKaplan et al. 2020
PaperChinchillaHoffmann et al. 2022
PaperLoRAHu et al. 2021
PaperInstructGPTOuyang et al. 2022
CourseCS231nStanford
CourseCS224nStanford
CoursePractical Deep Learningfast.ai
ToolHugging FaceModel hub
ToolWeights & BiasesExperiment tracking
PersonAndrej Karpathy@karpathy
PersonYann LeCunMeta AI
BookMathematics for Machine LearningDeisenroth et al.
BookDive into Deep LearningZhang et al.
GitHubNVIDIA/cuda-samplesNVIDIA
ToolPapers With CodeBenchmarks
Interview QExplain gradient descent and its variants (SGD, Adam, AdaGrad).interview check
Interview QHow does attention scale similarity search?interview check
Interview QWhen does fine-tuning beat prompting?interview check
12 modules · 108 lessonsFull curriculum