Stars
Minimal reproduction of DeepSeek R1-Zero
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases (NeurIPS D&B 2024)
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
An easy way to host your own AI API and expose alternative models, while being compatible with "open" AI clients.
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
A natural language interface for computers
A standard framework for modelling Deep Learning Models for tabular data
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀
Implements sorting algorithm for directed acyclic as well as cyclic graphs. The directed cyclic graphs are sorted by determining the minimal amount of cyclic edges and optionally then also determin…
Official code for the paper "Task2Vec: Task Embedding for Meta-Learning" (https://arxiv.org/abs/1902.03545, ICCV 2019)
An autoML framework & toolkit for machine learning on graphs.
RepVGG: Making VGG-style ConvNets Great Again
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Codes for paper "Flexible Neural Representation for Physics Prediction".
Pytorch implementation for "Open Compound Domain Adaptation" (CVPR 2020 ORAL)
An elegant PyTorch deep reinforcement learning library.
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)
This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaof…
Distributionally robust neural networks for group shifts
Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"
Semi-supervised Domain Adaptation via Minimax Entropy
Code for the Lovász-Softmax loss (CVPR 2018)