Pinned Loading

1. antgroup/AEnt antgroup/AEnt Public

   An implementation of the regularization method "AEnt" introduced in "on entropy control in LLM-RL algorithms".

   Python 2

2. areal-project/AReaL areal-project/AReaL Public

   The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

   Python 5.7k 574

3. SEAL SEAL Public

   An implementation of SEAL: Safety-Enhanced Aligned LLM fine-tuning via bilevel data selection.

   Python 24 4

4. heshandevaka/XRIGHT heshandevaka/XRIGHT Public

   The official PyTorch implementation of ALRIGHT and MAXRIGHT algorithms for efficient trade-off in LLM post-training

   Python 13 1

5. penalized-bilevel-gradient-descent penalized-bilevel-gradient-descent Public

   An implementation of the penalty-based bilevel gradient descent (PBGD) algorithm and the iterative differentiation (ITD/RHG) methods.

   Python 19 4

6. AiPOD AiPOD Public

   Pytorch implementation of AiPOD and E-AiPOD.

   Python 5 2