GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
-
Updated
Jun 18, 2026 - Cuda
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
byte-pair-encodingHere are 132 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
c nlp training machine-learning deep-learning neural-network openmp cuda cublas language-model from-scratch byte-pair-encoding gpt2 llm bpe-tokenizer flashattention trasformer
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding.
A ridiculously fast Python BPE (Byte Pair Encoder) implementation written in Rust
python rust openai pypi-package bpe byte-pair-encoding huggingface tokenizers llm tiktoken bpe-tokenizer byte-pair-tokenizer
Python/Cython implementations and experimental data for the Pruned BPE and DH-BPE publications.
tokenizer tokenization bpe byte-pair-encoding subword-tokenization pre-tokenization pruned-bpe vocabulary-pruning dh-bpe minimum-token-dp-encoding
670 MB/s Swift tokenizer inspired by Marcel Roed’s gigatoken. Zero-copy, NEON/CRC32, WebAssembly, and Embedded Swift.
swift high-performance neon tokenizer zero-copy swift-package-manager webassembly wasm simd arm64 tokenization core-ai bpe byte-pair-encoding large-language-models llm tiktoken mlx-swift embedded-swift gigatoken
An educational Python project for learning tokenization step by step by building character-level, byte-level, and BPE tokenizers from scratch.
python nlp docker tokenizer text-processing tokenization educational-project bpe byte-pair-encoding regextokenizer llm subword-tokenization bpe-tokenizer byte-pair-tokenizer char-tokeneizer
High performance unsupervised text tokenization for Ruby
Byte-Pair Encoding (BPE) (subword-based tokenization) algorithm implementaions from scratch with python
python nlp natural-language-processing tokenizer data-preprocessing data-cleaning bpe byte-pair-encoding subword-tokenization
R package for Byte Pair Encoding based on YouTokenToMe
Byte-level byte pair encoding (BPE) in Haskell
Feature extraction from sequential data
natural-language-processing text-classification feature-extraction word-segmentation sequential-data vgram byte-pair-encoding
This is a tool that encrypts a sequence of words (or pieces of texts) using the AES-256 algorithm and encodes the encrypted result into a PNG image by linking each byte value to a specific color. It also decodes the before image to get back the original sequence of words
go golang encryption tdd clean-code wasm image-processing bit-manipulation aes-256 hexagonal-architecture byte-array bip39 png-decoder solid-principles encryption-decryption cold-wallet golang-wasm byte-pair-encoding pterm go-aes-256
The fastest tokenizer for LLMs, up to 30x+ faster.
Lightweight, header-only Byte Pair Encoding (BPE) trainer in modern C++17. Produces HuggingFace-compatible vocabularies for transformers and integrates with Modern Text Tokenizer.
nlp machine-learning natural-language-processing deep-learning tokenizer modern-cpp vocabulary transformers header-only text-processing no-dependencies tokenization c17 bpe byte-pair-encoding huggingface
Code repo for the paper "AutoGO: Automated Computation Graph Optimization for Neural Network Evolution", accepted to NeurIPS 2023.
deep-neural-networks deep-learning tensorflow tokenizer pytorch classification human-pose-estimation super-resolution semantic-segmentation neural-architecture-search pytorch-geometric byte-pair-encoding neurips-2023
Byte-Pair Encoding tokenizer for training large language models on huge datasets
python machine-learning deep-learning tokenizer chunking from-scratch bpe byte-pair-encoding large-language-models llm bpe-tokenizer
Генерация новостных заголовков
pytorch summarization reinforce abstractive-summarization pointer-generator byte-pair-encoding summatization
Add this topic to your repoTo associate your repository with the byte-pair-encoding topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |