jmaczan/bpe-tokenizer

Stars
2
Language
Python
License
GNU General Publi...
Created 6 months ago
Updated 6 months ago

jmaczan/bpe-tokenizer

jmaczan

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Byte-Pair Encoding tokenizer for training large language models on huge datasets

bulma-helpers

🍥 Library with Functional / Atomic CSS classes for Bulma framework

gdansk-ai

Full stack voice chatbot

basic-vue-chat

💬 Easy to use Vue chat

pff

Examine your Internet connection quality and status in terminal

text-to-ml

Homebrew AutoML using natural text. Like HuggingGPT + LangChain + type inference

asr-dysarthria

Research on Automatic Speech Recognition for dysarthric speech

Jupyter Notebook

0x6b73746b

🐱 Tree-Walk Interpreter

spellbook

🪄 Shell and Powershell scripts registry

tinyconv

🌸 Image processing with kernel and convolution

xiexie

🎐 Static site generator

openai-polling

Polling library for OpenAI Threads API

funkcja

🖇️ Log function body and name to browser's console

repeat-sh

🕰️ Repeat any shell command with interval

mac-addresses-scanner

🔦 Find MAC addresses of devices connected to a network

mlp-classifier

🤗 Multi-Layer Perceptron artificial neural network

deep-learning-pytorch

Deep Learning architectures implemented in PyTorch Lightning

csv-to-ml

🧌 Upload a CSV file and get an ML model

bpe.c

Byte-Pair Encoding tokenizer for training large language models on huge datasets. I don't know C, so most of the code comes from AI :D I hope to learn by rewriting it and making changes, fixes etc