Pinned Loading

1. swiss-ai/Megatron-LM swiss-ai/Megatron-LM Public

   Forked from NVIDIA/Megatron-LM

   Ongoing research training transformer models at scale

   Python 44 29

2. hot-mess-of-ai hot-mess-of-ai Public

   Python 31 1

3. epfml/llm-baselines epfml/llm-baselines Public

   nanoGPT-like codebase for LLM training

   Python 117 38

4. epfml/schedules-and-scaling epfml/schedules-and-scaling Public

   Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"

   Python 92 8

5. epfml/getting-started epfml/getting-started Public

   Python 30 16

6. swiss-ai/MoE swiss-ai/MoE Public

   some mixture of experts architecture implementations

   Python 27 3