🚀 Efficient implementations for emerging model architectures
- large-language-models
- machine-learning-systems
- natural-language-processing
- sequence-modeling
81,588 visible repositories in the index
169–192 of 813 · Most stars
🚀 Efficient implementations for emerging model architectures
Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.
A unified ecosystem and workspace for large-scale federated learning, bridging the gap between centralized model evolution and decentralized edge intelligence.
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
Claude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.
Democratizing Reinforcement Learning for LLMs
TranslatedHands-on 🐍 web crawlers for many kinds of websites and e-commerce data 🕷. Includes 🕸: Taobao products, WeChat official accounts, Dianping, Qichacha, job recruitment sites, Xianyu, Alibaba tasks, Cnblogs, Weibo, Baidu Tieba, Douban movies, Baotu (ibaotu.com), Quanjing (quanjing.com), Douban music, a provincial drug administration, Sohu News, machine learning text collection, FOFA asset collection, Autohome, National Bureau of Statistics, Baidu keyword indexed-page counts, spider pool directories, Toutiao (Today's Headlines), Douban movie reviews, Ctrip, Xiaomi App Store, Anjuke, Tujia homestays ❤️❤️❤️. WeChat crawler showcase project:
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
TranslatedAwesome Pretrained Chinese NLP Models, a collection of high-quality Chinese pretrained models, large models, multimodal models, and large language models
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Socket.IO integration for Flask applications.
Python package for doing RPA
OpenChat: Advancing Open-source Language Models with Imperfect Data
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
Automatically visualize your pandas dataframe via a single print! 📊 💡
TranslatedPicACG comic PC client(Windows, Linux, MacOS)
A supercharged AWS command line interface (CLI).
StarGAN - Official PyTorch Implementation (CVPR 2018)
Translated[Three Years of Interviews, Five Years of Mock Interviews] An interview resource platform for AIGC/LLM/AI Agent algorithm engineers. It covers practical interview and written-test experience and core, cross-cycle knowledge for the AI industry, including AIGC, LLM large models, AI Agents, embodied intelligence, traditional deep learning, computer vision, natural language processing, autonomous driving, machine learning, reinforcement learning, big data mining, world models, the metaverse, AGI, and more.
A Next-Generation Training Engine Built for Ultra-Large MoE Models