Tom Aarsen
Sentence Transformers, SetFit & NLTK maintainer, ML Engineer & Fellow @huggingface
This profile was put together from Tom's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Tom Aarsen works in ML & data science and AI engineering, based in Netherlands (huggingface). Sentence Transformers, SetFit & NLTK maintainer, ML Engineer & Fellow @huggingface. Public projects on GitHub include Attention Sinks (Extend existing LLMs way beyond the original training length with constant memory usage, without retraining), SpanMarkerNER (SpanMarker for Named Entity Recognition) and TTSTextNormalization (Convert English text from written expressions into spoken forms), mostly written in Python and Jupyter.
Projects 6
Attention Sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
github.comSpanMarkerNER
SpanMarker for Named Entity Recognition
github.comTTSTextNormalization
Convert English text from written expressions into spoken forms
github.comInflex
Natural Language Inflection in English
github.com- github.com
TwitchAIDungeon
Twitch Bot allowing chat to play AI Dungeon
TwitchMarkovChain
Twitch Bot for generating messages based on what it learned from chat
github.com