Pinned

1. ear ear Public

   Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"

   Python 43 4

2. ferret ferret Public

   A python package for benchmarking interpretability techniques on Transformers.

   Python 206 15

3. clip-italian/clip-italian clip-italian/clip-italian Public

   CLIP (Contrastive Language–Image Pre-training) for Italian

   Jupyter Notebook 173 17

4. MilaNLProc/simple-generation MilaNLProc/simple-generation Public

   A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.

   Python 23 2

5. MilaNLProc/interpretability-mt-gender-bias MilaNLProc/interpretability-mt-gender-bias Public

   Code associated with the paper "A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation".

   Python 3 1