Pinned Loading

1. sjelassi/ebft_openrlhf sjelassi/ebft_openrlhf Public

   Code for "Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models".

   Python 23

2. optimizers-llm optimizers-llm Public

   Code for "Deconstructing What Makes a Good Optimizer for Language Models"

   Python 3

3. openrlhf-pretrain openrlhf-pretrain Public

   Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"

   Python 30 3

4. McGillAISociety/mcgillaiwebsite McGillAISociety/mcgillaiwebsite Public

   The McGill AI Society Website

   JavaScript 7