ngram2vec
Four word embedding models implemented in Python. Supporting arbitrary context features
- 847
- Python
- 7 y ago
Four word embedding models implemented in Python. Supporting arbitrary context features
Go metrics for calculating string similarity and other string utility functions
[EMNLP 2020] Keep CALM and Explore: Language Models for Action Generation in Text-based Games
A minimum viable Markov gibberish generator in 32 lines of Python, inspired by the legendary Mark V. Shaney program of 1980s
Kotlin multiplatform library offering various algorithms to measure string similarity and distance
Training repo for Toy GPT: bigram model + small domain corpus (010_llm_glossary.txt)
Training repo for Toy GPT: unigram + small neutral corpus (000_cat_dog.txt)
Use numpy to realize bert's achitecture of transformers manually, as well as n-gram, bayes, LSTM