alphadl Goto Github PK

followers: 182.0 following: 182.0 repos: 382.0 gists: 0.0

Name: Liang Ding

Type: User

Company: JD Explore Academy, JD.com Inc.

Bio: NLP/ML researcher (developing LLM and exploring its way to human-centric AGI).

Twitter: liangdingNLP

Location: Shanghai(CN) & Sydney(AU)

Blog: liamding.cc

Hi there

🙋‍♂️ I am a principal researcher of LLM at an AGI startup, and worked at JD Explore Academy and Tencent AI Lab, and previously Ph.D. at Univ. of Sydney.

🔭 Working on deep learning for NLP, including language model pretraining, language understanding, generation, and translation.

💪 I'm keen on bodybuilding (5 years+), marathon (completed first half marathon (126min) in Beijing-2016 and most recent half marathon (86min) in Sydney-2019😅. will resume training in 2024💪🏻).

🥗 I (once😅) enjoy cooking.

🐈 I like to spend Sundays with my cats (two from 2020-2023, one from 2023).

Star History ⭐️

Liang Ding's Projects

juliaml

Machine Learning Algorithms (Julia)

kaggle_lstm_pronunciation_pred

lstm based model for kaggle pronunciation prediction

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

keras_npi

NPI(Neural Programmer-Interpreters) implementation with Keras

keywords_extract

knmt

A Neural Machine Translation implementation in Chainer

knowledge-distillation

Transfer knowledge from a large DNN or an ensemble of DNNs into a small DNN

labse

Language-agnostic BERT Sentence Embedding (LaBSE)

lama

LAnguage Model Analysis

lamtram

lamtram: A toolkit for neural language and translation modeling

lcnat

learning_to_execute

Learning to Execute

lightnet

Transparent deep learning in hundreds of lines of code.

lihang-code

《统计学习方法》的代码实现

lihang_book_algorithm

致力于将李航博士《统计学习方法》一书中所有算法实现一遍

llmpapers

Papers & Works for large languange models (ChatGPT, GPT-3, Codex etc.).

lookahead.pytorch

lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

lstm

machine_learning

Summary of Machine Learning: A Probabilistic Perspective book

machinelearning_zhou

coding for book 《ML》by lian

marian

Fast Neural Machine Translation in C++

mask-predict_with_prober

A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.