Code for studying the super weight in LLM

AlphaFold 3 inference pipeline.

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

[NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models

A simple, performant and scalable Jax LLM!

The IterativeDisplay class for MATLAB is designed to assist in displaying iterative process updates in a structured and customizable manner.

A playbook for systematically maximizing the performance of deep learning models.

TruthfulQA: Measuring How Models Imitate Human Falsehoods

Simple clipboard manager to be integrated with rofi - Static binary available

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

The official Meta Llama 3 GitHub site

LLM inference in C/C++

Automatically exported from code.google.com/p/latex-bibitemstyler

Graph-Mamba: Towards Long-Range Graph Sequence Modelling with Selective State Spaces

Exact Combinatorial Optimization with Graph Convolutional Neural Networks (NeurIPS 2019)

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Mamba SSM architecture

A Latex style and template for paper preprints (based on NIPS style)

良性过拟合现象是深度学习方法揭示的关键奥秘之一：深度神经网络即使完全拟合噪声训练数据，似乎也能很好地预测。

[NeurIPS'18, Spotlight oral] "Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds", by Xiaohan Chen*, Jialin Liu*, Zhangyang Wang and Wotao Yin.

[ICLR 2023] "On Representing Mixed-Integer Linear Programs by Graph Neural Networks" by Ziang Chen, Jialin Liu, Xinshang Wang, Jianfeng Lu, Wotao Yin.

Optimization-based deep learning models can give explainability with output guarantees and certificates of trustworthiness.

LotteryFL: Empower Edge Intelligence with Personalized and Communication-Efficient Federated Learning (2021 IEEE/ACM Symposium on Edge Computing)

Fit interpretable models. Explain blackbox machine learning.