Pinned Loading

1. ETHOS ETHOS Public

   ETHOS: Efficient Transformers via Hypernetwork-Organized Sparsity

   Jupyter Notebook 7

2. moe-scaling moe-scaling Public

   Scaling Laws for Mixture of Experts Models

   Jupyter Notebook 16 1

3. llm720 llm720 Public

   Second Generation of Large Language Models

   Python 21 1