DingDing
Student at tsinghua
Beijing, China
Summary
🤩
RockstarDingDing is an experienced software engineer and student based in Beijing with eight years of hands-on experience focused on NLP and infrastructure tooling. At Tsinghua-affiliated open-source projects like thunlp/OpenPrompt and OpenDelta, they strengthened training pipelines with checkpointing, multi-GPU support, and refactors that improved usability and documentation. Comfortable in back-end development and DevOps roles, DingDing combines pragmatic code maintenance with a knack for making research-oriented libraries production-ready. Their contributions show attention to detail—bug fixes and example additions that lower the barrier for new users—while enabling efficient parameter-efficient tuning workflows. Passionate about NLP, they bridge academic interest and engineering discipline to ship reliable tooling for the research community.
8 years of coding experience
Github Skills (14)
pytorch10
deeplearning-ai10
nlp10
deep-learning10
nlpjs10
python10
refactor9
checkpointing9
logging9
refactoring9
checkpoint9
regular-expression9
transformer9
documentation8
Programming languages (10)
Github contributions (5)
thunlp/OpenPrompt
Sep 2021 - Jul 2022
An Open-Source Framework for Prompt-Learning.
Role in this project:
Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:1 release, 86 commits, 3 PRs in 9 months
Contributions summary:DingDing primarily contributed to the enhancement of the training process by adding checkpointing functionality and modifying the logging directory for improved efficiency. They also fixed documentation bugs, demonstrating attention to detail and a focus on code maintainability. In addition, the user added support for multi-GPU environments, improving the overall usability of the project.
natural-language-understandingpre-trained-language-modelsdialogue-systemsnatural-language-processingprompts
thunlp/OpenDelta
Feb 2022 - Nov 2022
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)
Role in this project:Back-end Developer
Back-end DeveloperContributions:2 releases, 103 commits, 17 PRs in 8 months
Contributions summary:DingDing primarily focused on refactoring and improving the `opendelta` library. Their commits included merging regular expression and documentation updates, indicating efforts to enhance code clarity and usability. They also addressed code structure and functionality by merging branches and adding example files. The user demonstrates proficiency in modifying existing code structures and incorporating new features within the context of a parameter-efficient-tuning library.
nlpdeltadeep-learningmachine-learningparameter
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.