PinnedPramod Goyal@goyal__pramodMay 11, 2025Most influential LLM papers and the ideas they introduced (post 2017) A long thread 🧵15153533532.4K2.4K299K299K
Pramod Goyal@goyal__pramodMay 12, 2025Gpt-2 is just 174 lines of code... How crazy is that1101101791793.8K3.8K862K862K
Pramod Goyal@goyal__pramodSep 15, 2025Btw, this is the best book ever on Linear Algebra. Extremely interactive and beautiful visuals21213613613.2K3.2K160K160K
Pramod Goyal@goyal__pramodJul 20, 2025A beautiful visual blog, where you can change values, interact, and see what each head does exactly inside the transformer.12123973973K3K251K251K
Pramod Goyal@goyal__pramodSep 15, 2025One of the best technical blogs I have ever read period!11112882883K3K181K181K
Pramod Goyal@goyal__pramodJul 24, 2025Trust me when I say you won't regret reading this39392042042.8K2.8K198K198K
Pramod Goyal@goyal__pramodMay 21, 2025Now that Google has released a text diffusion model, it's time to read this paper.26262962962.5K2.5K125K125K
Pramod Goyal@goyal__pramodJul 10, 2025A beautiful paper that goes through Diffusion step by step, explaining the entire math of it from the beginning.663343342.5K2.5K179K179K
Pramod Goyal@goyal__pramodMar 22, 2025The OG blog on how PyTorch actually works Internally.771881882.1K2.1K146K146K
Pramod Goyal@goyal__pramodJul 4, 2025Today is the day I truly understood why attention works Not just for words, but images, audio, video. But everything else.11111931932.1K2.1K331K331K
Pramod Goyal@goyal__pramodJun 13, 2025Some blogs change your perception, and this one by Andrej Karpathy is one of those.991821822K2K141K141K
Pramod Goyal@goyal__pramodSep 5, 2025The greatest explanation of PCA you will ever read10101771771.9K1.9K144K144K
Pramod Goyal@goyal__pramodMar 23, 2025The best way to learn PyTorch is by building something with it. Consider checking out my blog where I help you, build transformers using PyTorch from scratch13132542541.9K1.9K112K112K
Pramod Goyal@goyal__pramodApr 27, 2025There is no better blog (that I have found) which explains intuitively WHY momentum works.881341341.7K1.7K114K114K