Pinned Loading

1. Awesome-LLM-Compression-Safety Awesome-LLM-Compression-Safety Public

   A curated collection of papers and resources on the safety impacts of model compression in Large Language Models (LLMs), highlighting key challenges, risks, and recent advances.

   3

2. histoires-morales histoires-morales Public

   Histoires Morales: A French Dataset for Assessing Moral Alignment (NAACL 2025)

   Python 3

3. hate-prototypes hate-prototypes Public

   Code for the paper "HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection"

   Jupyter Notebook

4. fair-gptq fair-gptq Public

   Python

5. la-tda la-tda Public

   Code for EACL Workshop paper Can BERT eat RuCoLA? Topological Data Analysis to Explain

   Jupyter Notebook 7

6. grammarticle grammarticle Public

   Grammar checker for English article usage

   Python 1