Stars
This is the official repository for our paper "Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning" published in ICRL 2026.
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
This hands-on lab aims to alleviate some of that headache by demonstrating how to create/augment a QnA dataset from complex unstructured data, assuming a real-world scenario. The sample aims to be …
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Making large AI models cheaper, faster and more accessible
Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.
Yet another elegant Wiz Note Client, which was built with Quasar UI Framework and based on Electron.
C++ Parallel Computing and Asynchronous Networking Framework
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Fast and Accurate ML in 3 Lines of Code
DezhouKV的C++版本实现(C++ implementation of DezhouKV database)
Python code for "Probabilistic Machine learning" book by Kevin Murphy
yangfly / caffe
Forked from BVLC/caffeCaffe with contrib applications out of box.
Code for 3rd Place Solution in Face Anti-spoofing Attack Detection Challenge @ CVPR2019,model only 0.35M!!! 1.88ms(CPU)
Visualizer for neural network, deep learning and machine learning models
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
This is a mxnet version implementation of SSR-Net for age and gender Estimation
Use TensorRT API to implement Caffe-SSD， SSD（channel pruning）， Mobilenet-SSD
a casual work about retraining to optimize mtcnn Pnet and ONet. it can achieve 100+fps on CPU with minSize 60 (1920x1080) on intel i7 6700k