Pinned Loading

1. llava-rlhf/LLaVA-RLHF llava-rlhf/LLaVA-RLHF Public

   Aligning LMMs with Factually Augmented RLHF

   Python 399 30

2. DIFUSCO DIFUSCO Public

   Code of NeurIPS paper: arxiv.org/abs/2302.08224

   Python 266 58

3. IBM/SALMON IBM/SALMON Public archive

   Self-Alignment with Principle-Following Reward Models

   Python 171 13

4. easy-to-hard easy-to-hard Public

   Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

   Python 124 11

5. RECITE RECITE Public

   Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI

   Python 96 11

6. gpt-accelera gpt-accelera Public

   Simple and efficient pytorch-native transformer training and inference (batched)

   Python 78 6