Tutorials

Long-form notes on theory, probability, optimization, language, and deep learning.

Intrinsic Dimension Estimation

Tensorized and parallelizable pytorch implementation of the algorithm for intrinsic dimension estimation.
Intrinsic DimensionGeometryPyTorchTwo-NNMLE

Generating Random Variables and Stochastic Processes, Generative Flow Networks (GFlowNets)

Practical tutorial about GFlowNets, MCMC, Metropolis-Hasting, Gibbs sampling, and related stochastic simulation methods.
Inverse Transform SamplingAcceptance-Rejection MethodMCMCMetropolis-HastingGibbs samplingMetropolis-adjusted LangevinImportant SamplingGflowNets

Pre-train and Fine-tune a Language Model with 🤗 Transformers

My tutorial on how to pre-train a causal and masked language model with the Hugging Face transformers library.
TransformersLanguage ModelsHugging Face

Word embeddings

My original tutorial on word embeddings, from Bag of Words and TF-IDF to Word2Vec and GloVe.
NLPGloveWord2VecBag of wordsTF-IDF