Liyuan Liu

RAdam. On the Variance of the Adaptive Learning Rate and Beyond

LM-LSTM-CRF. Empower Sequence Labeling with Task-Aware Language Model

Transformer-Clinic. Understanding the Difficulty of Training Transformers

LD-Net. Language Model Pruning for Sequence Labeling

LightNER. Inference with state-of-the-art models (pre-trained by LD-Net / AutoNER / VanillaNER / ...)

ReHession. Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach

Torch-Scope. A Toolkit for Training, Tracking, Saving Models and Syncing Results

ArabicNER. Arabic NER system with a strong performance

Vanilla_NER. Vanilla Sequence Labeling w. Char-LSTM-CRF

Raw-to-End. Raw-to-End Name Entity Recognition in Social Media

Content-Propagation. Community Detection Based on Structure and Content

Fast-Furious-Paper. Reading Group @ DMG

ReinMax. Beyond Straight-Through

clerk. Python

hugo-academic. 📝 The website builder for Hugo. Build and deploy a beautiful website in minutes!

lstm-char-cnn. LSTM language model with CNN over characters

TransformerEngine-MoE. A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

torch-rnn. Efficient, reusable RNNs and LSTMs for torch

livebench_phimoe. Python

word2vec_0. This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

awesome-rnn. Recurrent Neural Network - A curated list of resources dedicated to RNN

entity-recognition-datasets. A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.

COVID-19-TweetIDs. The repository contains an ongoing collection of tweets IDs associated with the novel coronavirus COVID-19 (SARS-CoV-2), which commenced on January 28, 2020.

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

docker-ufrii-airprint. Dockerfile

LiyuanLucasLiu.github.io. S-Theme: Simple & Beautiful Responsive Jekyll theme.

awesome-community-detection. A curated list of community detection techniques.