Chris McCormick

word2vec_commented. Commented (but unaltered) version of original word2vec C implementation.

inspect_word2vec. Python code for checking out Google's pre-trained, 3M word Word2Vec model

MinHash. Example Python code for comparing documents using MinHash

dbscan. A simple implementation of DBSCAN in Python

LSA_Classification. Text classification example in Python using Latent Semantic Analysis (LSA)

wiki-sim-search. Similarity search on Wikipedia using gensim in Python.

hog_matlab. Matlab implementation of the HOG descriptor for pedestrian detection

simsearch. Python tools for performing similarity searches on text documents.

word2vec_matlab. MATLAB

summarize-long-pdfs. Long Document Summarization with ChatGPT

mlpack-examples. Some ready-to-run C++ examples for mlpack

shared-subspaces. Research code exploring shared subspaces in attention and feedforward networks. Includes SVD analysis of pre-trained models, experiments with shared output projections, and latent-space-efficient Transformer variants.

kfold_cv. k-Fold Cross-Validation in Matlab

rbfn_matlab. Radial Basis Function Network implementation in Matlab

brute_knn_benchmarks. Performance measurements on brute-force k-NN implementations on GPU and CPU

llm-tuning-examples. A collection of fine-tuning examples from others, with my comments added.

chrisjmccormick.github.io. My machine learning blog, built on Poole

simpletransformers. Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

Balzac-for-Jekyll. Your favorite AnchorCMS theme, now for Jekyll!

personal-site. My personal site covering all my hobbies and interests outside of work

modded-nanochat. For all of the optimizations that are too complex