Skip to content
View lingengyuan's full-sized avatar
🎯
Focusing
🎯
Focusing
14 followers · 24 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: YOLOAchievement: Pull Sharkx2

Block or report lingengyuan

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. 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
lingengyuan/README.md

Hugh Lin · 林耿塬

I build tools for AI-assisted development and knowledge management. I also reproduce language-model research on Apple Silicon, with code, experiment logs, and results.

Tools and workflows

Project What it does
my-skills Agent skills for technical writing, Obsidian, Git, and Mermaid diagrams.
x-algorithm-simulator An interactive simulator of X's public recommendation pipeline, using local fixtures.

Local LLM experiments

Project What I explore
gpt2-from-scratch GPT-2 training, LoRA, evaluation, and inference on an M5 MacBook Air.
qjl-mlx QJL and TurboQuant KV-cache quantization with MLX and PyTorch reference checks.
minimind-autoresearch Training and evaluation experiments for a 26M Chinese language model.

Open-source contributions

I contribute fixes to Pele, a Mermaid-to-SVG renderer.

Main tools

Python · TypeScript · MLX · PyTorch

For project questions, please open an issue in the relevant repository.

Pinned Loading

  1. my-skills my-skills Public

    Agent skills for technical writing, Obsidian, Git, and Mermaid diagrams.

    Python 9 1

  2. x-algorithm-simulator x-algorithm-simulator Public

    Interactive simulator of the public X recommendation pipeline using local fixtures.

    TypeScript 5 1

  3. gpt2-from-scratch gpt2-from-scratch Public

    GPT-2 Small (124M) training, LoRA, evaluation, and inference experiments on Apple Silicon.

    Python

  4. qjl-mlx qjl-mlx Public

    QJL and TurboQuant KV-cache quantization with MLX and PyTorch reference checks.

    Python 3 2

  5. minimind-autoresearch minimind-autoresearch Public

    Training and evaluation experiments for a 26M Chinese language model on Apple Silicon.

    Python 5