Jinjie Ni

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

EasyLiterature. EasyLiterature is an open-sourced, Python-based command line tool for automatic literature management.

MixEval. The official evaluation suite and dynamic data release for MixEval.

dlms-are-super-data-learners. The official github repo for "Diffusion Language Models are Super Data Learners".

OpenMoE2. The official repo for "OpenMoE 2: Sparse Diffusion Language Models".

Quokka. The official github repo for "Training Optimal Large Diffusion Language Models", the first-ever large-scale diffusion language models scaling law..

MixEval-X. The official github repo for MixEval-X, the first any-to-any, real-world benchmark.

Grouped-Head-Attention. Code for the paper Finding the Pillars of Strength for Multi-Head Attention.

open-instruct. Python

Top-Conference-WeChat-Group.