Tom Aarsen

attention_sinks. Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

SpanMarkerNER. SpanMarker for Named Entity Recognition

TwitchMarkovChain. Twitch Bot for generating messages based on what it learned from chat

TTSTextNormalization. Convert English text from written expressions into spoken forms

TheNounProjectAPI. A Python wrapper allowing convenient access to the Noun Project API.

nltk_theme. Sphinx theme for NLTK

module_dependencies. Gather module dependencies of source code

Inflex. Natural Language Inflection in English

TwitchCubieBotGUI. Twitch Bot focusing on aggregating votes and averages from Twitch chat, with a GUI

TwitchWebsocket. Python Wrapper for easily connecting to Twitch and setting up a chat bot.

TwitchSaveMessages. Twitch bot to save API information from chat messages and more in a database.

TwitchWeather. Twitch bot which displays weather information of any town

TwitchSendMessage. Send singular messages from a Bot account to chat

TwitchUrbanDictionary. Twitch Bot to look up urban dictionary definitions and examples.

TwitchAIDungeon. Twitch Bot allowing chat to play AI Dungeon

TwitchCubieBot. Twitch Bot focusing on aggregating votes and averages from Twitch chat

Binance-Portfolio-Reallocation-Showcase. Compare the performance of a Portfolio Reallocation Bot against holding on to the coins, for any (number of) Binance coins.

model2vec. Model2Vec: Distill a Small Fast Model from any Sentence Transformer

bm25s. BM25S is an ultra-fast lexical search library that implements BM25 using scipy

ipex-llm. Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with llama.cpp, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc.

tokenizers. 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

TwitchGoogleTranslate. Twitch Bot which can hilariously modify its input using Google Translate

TwitchMMLevelQueueGUI. Twitch bot which create a queue for Mario Maker 2 Levels from chat, with a GUI

create-llama. The easiest way to get started with LlamaIndex

AnglE. Angle-optimized Text Embeddings | 🔥 SOTA on STS and MTEB Leaderboard

TwitchDeathCounter. Twitch Bot that allows chat to keep track of a Death Counter

IRSpellingCorrection. Rule-based spelling correction as query pre-processing on IR systems

TwitchSuggestDinner. Twitch bot that will suggest what you should get for dinner!

setfit. Efficient few-shot learning with Sentence Transformers

blog. Public repo for HF blog posts

AIR-Bench. AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Verba. Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

TwitchRandomRecipe. Allow chat to generate some horrible recipes

EMO. [ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)

deep-learning-pytorch-huggingface. Jupyter Notebook

canopy. Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone

llama_index. LlamaIndex (GPT Index) is a data framework for your LLM applications

classy-classification. This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classificaiton with Huggingface..

ColBERT. ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

embetter. just a bunch of useful embeddings

tomaarsen.com-frontend. Frontend for www.tomaarsen.com

TwitchDialCheck. Twitch Bot to detect and rate DIAL-in checks.

TwitchPackCounter. Twitch Bot to keep track of gift subscriptions