implementation of BPE algorithm and training of the tokens generated

self made byte-pair-encoding tokenizer

Natural Language Processing course assignments @ University of Tehran

This repository is reimplementation of Transformer model which was introduced in 2017 NeurIPS paper "Attention is all you need"

Byte Pair Encoding (BPE) in the Zig programming language (0.13.0)

tokenizer for large-scale language models (GPT, Claude, Llama, etc.)

Byte-pair Algorithm used in GPT Tokenization based on the paper "Language Model are unsupervised multitask learners"

TF-IDF Calculation

A pure Python implementation of Byte Pair Encoding (BPE) tokenizer. Train on any text, encode/decode with saved models, and explore BPE tokenization fundamentals.

Byte Pair Encoding (BPE)

Strings Tokenization with Byte Pair Encoding (BPE).

A web app to compare pre-built or self-built tokenizers

A python package to build a corpus vocabulary using the byte pair methodology and also a tokenizer to tokenize input texts based on the built vocab.

From-scratch Marathi BPE tokenizer with Flask API and web interface for encoding/decoding Marathi text using Byte Pair Encoding algorithm.

[Rust] Unofficial implementation of "SuperBPE: Space Travel for Language Models" in Rust

A lightweight, from-scratch implementation of Byte Pair Encoding (BPE) tokenization in Python.

This project implements a tokenizer based on the Byte Pair Encoding (BPE) algorithm, with additional custom tokenizers, including one similar to the GPT-4 tokenizer.

Java library implementing Byte-Pair Encoding Tokenization