Pinned Loading

1. MegaDLMs MegaDLMs Public

   GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.

   Python 12 2

2. XueFuzhao/OpenMoE XueFuzhao/OpenMoE Public

   A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

   Python 1.6k 84

3. NVIDIA/Megatron-LM NVIDIA/Megatron-LM Public

   Ongoing research training transformer models at scale

   Python 14k 3.2k

4. MixEval MixEval Public

   The official evaluation suite and dynamic data release for MixEval.

   Python 250 41

5. deepseek-ai/DeepSeek-MoE deepseek-ai/DeepSeek-MoE Public

   DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

   Python 1.8k 294

6. EvolvingLMMs-Lab/lmms-engine EvolvingLMMs-Lab/lmms-engine Public

   A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

   Python 453 15