Popular repositories Loading

1. gated_attention gated_attention Public

   The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

   Jupyter Notebook 390 22

2. EMoE EMoE Public

   Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]

   Python 37 4

3. RMoE RMoE Public

   Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)

   Jupyter Notebook 27 1

4. EEG-Cross-Subject-Emotion-Recognition EEG-Cross-Subject-Emotion-Recognition Public

   Python 10

5. HMA HMA Public

   HMA: Heterogenous Memory Augmented Neural Networks

   Python 5

6. Tuning-keys-v.s.-values Tuning-keys-v.s.-values Public

   Official PyTorch Implementation of Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers [Tiny Paper @ ICLR 2024]

   Python 4