Skip to content
View wenzhaoabc's full-sized avatar
8 followers ยท 11 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: StarstruckAchievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: StarstruckAchievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Block or report wenzhaoabc

Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
wenzhaoabc/README.md

Hi, there ๐Ÿ‘‹

๐Ÿง‘โ€๐Ÿ’ป About Me

Currently pursuing my Master's degree while bridging the gap between theory and implementation. My interests:
  • ๐Ÿค– LLM Post-training (RLHF / PPO / GRPO)
  • ๐Ÿง  Reinforcement Learning for decision systems
  • ๐Ÿ”Ž Retrieval-Augmented Generation (RAG)
  • ๐Ÿ›ก๏ธ Reliability / safety / stability

๐Ÿ›  Skills

Python PyTorch Transformers TRL
Java Golang Docker Linux Node.js

๐Ÿ“ซ Contacts

Email GitHub

Pinned Loading

  1. llm-tap-rl llm-tap-rl Public

    Reinforcement Learning for LLM

    Jupyter Notebook 38 1

  2. mmkg-rag mmkg-rag Public

    Enhancing Retrieval-Augmented Generation with Multi-Modal Knowledge Graph Integration

    Python 15 2

  3. verl-project/verl verl-project/verl Public

    verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

    Python 22.2k 4.2k

  4. minillm minillm Public

    A lightweight implementation of LLMs with PyTorch and Transformers.

    Python 3

  5. tinyhttpd tinyhttpd Public

    tinyhttpd

    C 3

  6. o8oo8o/WebCurl o8oo8o/WebCurl Public

    ๆž็ฎ€็ฝ‘้กต็‰ˆAPI่ฐƒ่ฏ•็ฅžๅ™จ

    HTML 597 91