Skip to content
View matrix72c's full-sized avatar
21 followers · 35 following

Organizations

@NJUPT-SAST

Block or report matrix72c

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
matrix72c/README.md

Hi there 👋

I'm Matrix72, a PhD student studying Computer Science at Shanghai AI Lab and Zhejiang University.

My research focuses on trustworthy LLMs and ML systems.

Systems

Building tools and contributing to the InternLM ecosystem.

XTuner   XTuner stars   XTuner merged PRs
Training infrastructure for large language models.

LMDeploy   LMDeploy stars   LMDeploy merged PRs
Efficient LLM inference and serving.

Lagent   Lagent stars   Lagent merged PRs
A lightweight framework for LLM agents.

Flotilla   Flotilla stars   Creator
A multi-sandbox orchestration framework I built.

Trustworthy AI

REX   REX stars   Creator
Relocating hazardous knowledge into removable experts in MoE models.

RobustCBM   RobustCBM stars   Creator
Improving adversarial robustness in concept-based models while preserving effective human intervention.

Blog · Email

Pinned Loading

  1. flotilla flotilla Public

    Run Docker Compose task environments on sandbox platforms, one sandbox per service.

    Python 2 1

  2. RobustCBM RobustCBM Public

    Jupyter Notebook 1

  3. AI45Lab/REX AI45Lab/REX Public

    Code for paper "Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models"

    Python 7

  4. lagent lagent Public

    Forked from InternLM/lagent

    A lightweight framework for building LLM-based agents

    Python

  5. lmdeploy lmdeploy Public

    Forked from InternLM/lmdeploy

    LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

    Python

  6. xtuner xtuner Public

    Forked from InternLM/xtuner

    A Next-Generation Training Engine Built for Ultra-Large MoE Models

    Python