Tianyang Lin

@nil0x9 · User

GitHub profile ↗ · Compare

LLM Pretrain

Shanghai61 followers18 repositories

Repositories

nil0x9/flash-muon

Flash-Muon: An Efficient Implementation of Muon Optimizer

★ 263PythonForks 17

nil0x9/AReaL

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

★ 0Forks 0

nil0x9/markview.nvim

A hackable markdown, Typst, latex, html(inline) & Asciidoc previewer for Neovim

★ 0LuaForks 0

nil0x9/FlashQLA

high-performance linear attention kernel library built on TileLang

★ 0Forks 0

nil0x9/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

★ 0Forks 0

nil0x9/mmengine

OpenMMLab Foundational Library for Training Deep Learning Models

★ 0Forks 0

nil0x9/xtuner

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

★ 0PythonForks 0

nil0x9/plainLM-1

Minimal pretraining script for language modeling in PyTorch. Supporting torch compilation and DDP. It includes a model implementation and a data preprocessing.

★ 0Forks 0

nil0x9/Muon

Muon: An optimizer for hidden layers in neural networks

★ 0Forks 0

nil0x9/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

★ 0PythonForks 0

nil0x9/nanoGPT-mup

The simplest, fastest repository for training/finetuning medium-sized GPTs.

★ 0Forks 0