Alisa Liu

proxy-tuning. Code associated with Tuning Language Models by Proxy (Liu et al., 2024)

DExperts. code associated with ACL 2021 DExperts paper

ambient. Code and data associated with the AmbiEnt dataset in "We're Afraid Language Models Aren't Modeling Ambiguity" (Liu et al., 2023)

wanli. code associated with WANLI dataset in Liu et al., 2022

tokenizer-attack. Official implementation of "Data Mixture Inference: What do BPE tokenizers reveal about their training data?"

tokenizers-superbpe. patched version of tokenizers v0.20.1

hugo-alisawuffles.github.io. HTML

quizbey. Python

mafia. Python

nussl-1. A simple audio source separation library built in python

hugo-blog-theme. Jupyter Notebook

olmo-core-doc. Documentation for OLMo-core