JOHNNY-fans

PsycheChat. Python

Travel-on-the-ICD-Tree. Python

Rank4Gen. Python

youtu-embedding. Youtu-Embedding is an industry-leading, general-purpose text representation model developed by Tencent Youtu Lab.

youtu-agent. A simple yet powerful agent framework that delivers with open-source models

ReasonRank. [ACL 2026 Main] Repo for paper "ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability"

rank1. Test-time compute in information retrieval

MSMARCO-Passage-Ranking. MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, and passage ranking. A variant of this task will be the part of TREC and AFIRM 2019. For Updates about TREC 2019 please follow This Repository Passage Reranking task Task Given a query q and a the 1000 most relevant passages P = p1, p2, p3,... p1000, as retrieved by BM25 a succeful system is expected to rerank the most relevant passage as high as possible. For this task not all 1000 relevant items have a human labeled relevant passage. Evaluation will be done using MRR

TFRank. Python

EasyOffer. 《EasyOffer》（<大模型面经合集>）是针对LLM宝宝们量身打造的大模型暑期实习Offer指南，主要记录大模型暑期实习和秋招准备的一些常见大厂手撕代码、大厂面经经验、常见大厂思考题等；小白一个，正在学习ing......有问题各位大佬随时指正，希望大家都能拿到心仪Offer！

RRNorm. Python

DisenDiff. [CVPR`2024, Oral] Attention Calibration for Disentangled Text-to-Image Personalization

KG-o1. Python

PASTA. Pan-Tumor Radiology Foundation Model Utilizing Synthetic Training Data for Advanced Oncological Insights

MedEureka. Python

MinosEval. Jupyter Notebook

RankNorm. Jupyter Notebook

simple-simcse-ja. Exploring Japanese SimCSE

text_embedding. 一个用于训练句子embedding的工具，支持Cosent以及Simcse、infonce

MedOdyssey. Python

paper-reading. 深度学习经典、新论文逐段精读

Counting-Stars. Counting-Stars (★)

medical-books. Open sourece medical books in LaTeX. LaTeX写的中文开源医学书籍

uniem. unified embedding model

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

PULSE-EVAL. PULSE-EVAL

one-api. LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

MedLSAM. MedLSAM: Localize and Segment Anything Model for 3D Medical Images

PULSE. PULSE: Pretrained and Unified Language Service Engine

NormPULSE. Vue

Megatron-DeepSpeed-Llama. Python

OpenPrompt. An Open-Source Framework for Prompt-Learning.

NLPDataSet. 记录本人整理的一些数据集

Paper-Writing-Tips. MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

awesome-interview. 剑指前端 Offer

HowToCook. Programmer's guide about how to cook at home.

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

KBQA-for-Diagnosis. Knowledge Graph,Question Answering System，基于知识图谱和向量检索的医疗诊断问答系统

bert4keras. keras implement of transformers for humans

uni-app. A cross-platform framework using Vue.js

movie_recommender. MovieLens based recommender system.使用MovieLens数据集训练的电影推荐系统。

wechat-weapp-2048. 微信小程序-2048小游戏

gobang_AI. 基于博弈树α-β剪枝搜索的五子棋AI

KGQA-Based-On-medicine. 基于医药知识图谱的智能问答系统

KBQA-BERT. 基于知识图谱的问答系统，BERT做命名实体识别和句子相似度，分为online和outline模式