诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

算法竞赛模板库 by 灵茶山艾府 💭💡🎈

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

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

A modular RL library to fine-tune language models to human preferences

Rapid fuzzy string matching in Python using various string metrics

中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

Production First and Production Ready End-to-End Speech Recognition Toolkit

A curated list of awesome papers related to pre-trained models for information retrieval (a.k.a., pretraining for IR).

This repo contains the Hugging Face Deep Reinforcement Learning Course.

System for AI Education Resource.

Lecture notes, projects and other materials for Course 'CS219 Advanced Programming' at Southern University of Science and Technology.

Memray is a memory profiler for Python

Implement Statistical Learning Methods, Li Hang the hard way. 李航《统计学习方法》一书的硬核 Python 实现

Simple example of FastAPI + Celery + Triton for benchmarking

A quickstart and benchmark for pytorch distributed training.

Dialogue State Tracking (DST) Papers, Datasets, Resources 🤩

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing…

深度学习经典、新论文逐段精读

MLNLP：本仓库整理人工智能会议（如 ACL、EMNLP、NAACL、COLING、AAAI、IJCAI、ICLR、NeurIPS、ICML 等）中开源代码的论文。

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

Some basic examples of playing with RL

超轻量级bert的pytorch版本，大量中文注释，容易修改结构，持续更新

Prefix-Tuning: Optimizing Continuous Prompts for Generation

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

dialogbot, provide search-based dialogue, task-based dialogue and generative dialogue model. 对话机器人，基于问答型对话、任务型对话、聊天型对话等模型实现，支持网络检索问答，领域知识问答，任务引导问答，闲聊问答，开箱即用。