Pinned Repositories
clip-italian
CLIP (Contrastive Language–Image Pre-training) for Italian
confidence_intervals
Simple evaluation of classification confidence intervals.
ear
Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"
ferret
A python package for benchmarking interpretability techniques on Transformers.
interpretable-trading
l3wrapper
A lightweight Python 3 wrapper around the binaries of the L3 associative classifier.
multilingual-asr-gender-gap
Code associated with the paper "Multilingual Speech Models for Automatic Speech Recognition Exhibit Gender Performance Gaps."
speech-models-on-telegram
interpretability-mt-gender-bias
Code associated with the paper "A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation".
simple-generation
A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.
g8a9's Repositories
g8a9/ferret
A python package for benchmarking interpretability techniques on Transformers.
g8a9/ear
Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"
g8a9/multilingual-asr-gender-gap
Code associated with the paper "Multilingual Speech Models for Automatic Speech Recognition Exhibit Gender Performance Gaps."
g8a9/speech-models-on-telegram
g8a9/confidence_intervals
Simple evaluation of classification confidence intervals.
g8a9/sherlook
g8a9/yet_another_jax_transformer
g8a9/.dotfiles
g8a9/benchmarking-xai-private
g8a9/bert-in-cognition
g8a9/bertalign
Multilingual sentence alignment using sentence embeddings
g8a9/boostsa
Tool to compute bootstrap sampling significance test
g8a9/building-bridges-gender-fair-german-mt
g8a9/contextualizing-hate-speech-models-with-explanations
Official code release for ACL 2020 paper "Contextualizing Hate Speech Classifiers with Post hoc Explanation"
g8a9/downloading-scripts
g8a9/e-pluribus-unum-evalrs-2022
Repo containing code and data for the analysis presented in: "E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems"
g8a9/evalRS-CIKM-2022
Official Repository for EvalRS @ CIKM 2022: a Rounded Evaluation of Recommender Systems
g8a9/g8a9
g8a9/graphics
Graphical illustrations
g8a9/inseq
Interpretability for sequence generation models 🐛 🔍
g8a9/ita-eval
A framework for few-shot evaluation of language models.
g8a9/KE-complex_modifications
Karabiner-Elements complex_modifications rules
g8a9/mt_gender
g8a9/multi-modal-emotion
g8a9/questovirgolettatoesiste
g8a9/thermostat
Collection of NLP model explanations and accompanying analysis tools
g8a9/thoughts
Personal blog?
g8a9/training-scripts
g8a9/twitterknife
g8a9/wowchemy-website