Skip to content
View yushengsu-thu's full-sized avatar
94 followers · 70 following

Achievements

Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLOAchievement: Starstruck

Achievements

Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLOAchievement: Starstruck

Highlights

  • Pro

Organizations

@thunlp @ROCm

Block or report yushengsu-thu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yushengsu-thu/README.md

About Me (LLM #Researcher #Engineer):

My primary work and research focus on advancing models toward achieving AGI. Thus, I concentrate on the following key areas: (1) scaling pre-training and post-training frameworks, (2) improving efficiency, and (3) optimizing inference/agent engines to facilitate the rapid iterative development of foundation models. (Personal Website, Google Scholar).

Open Source Projects:

Contact:

Github Stats:

yusheng's github stats

Pinned Loading

  1. OpenBMB/AgentVerse OpenBMB/AgentVerse Public

    🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

    JavaScript 4.7k 458

  2. thunlp/Prompt-Transferability thunlp/Prompt-Transferability Public

    On Transferability of Prompt Tuning for Natural Language Processing

    Python 99 11

  3. hack-vimrc hack-vimrc Public

    my vim configure

    Vim Script 1

  4. volcengine/verl volcengine/verl Public

    verl: Volcano Engine Reinforcement Learning for LLMs

    Python 11.1k 1.8k

  5. verl verl Public

    Forked from volcengine/verl

    verl: Volcano Engine Reinforcement Learning for LLMs

    Python 2 2

  6. slime slime Public

    Forked from THUDM/slime

    slime is a LLM post-training framework aiming at scaling RL.

    Python 1