Pinned Loading

1. GPTNeo-RewardModel-Training GPTNeo-RewardModel-Training Public

   Training reward model based on pre-trained GPTNeo

   Jupyter Notebook 4

2. Multi-hop-QA-using-RL Multi-hop-QA-using-RL Public

   Multi-hop QA using RL framework

   Jupyter Notebook

3. textual-inversion textual-inversion Public

   Implementation of Textual Inversion

   Jupyter Notebook

4. per-pytorch per-pytorch Public

   Using Prioritized Experience Replay

   Python 1

5. vpg-pytorch vpg-pytorch Public

   Vanilla Policy Gradient

   Python